© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2245
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "not" and the verb "to be" in the same sentence

    oai_token-act-pair · gemini-2.0-flash

    terms related to permissibility or capability

    np_token-act-pair-logits · gpt-4o-mini

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ficulties
    -0.55
    RectangleBorder
    -0.55
    Not
    -0.53
    ValueStyle
    -0.52
     Normdatei
    -0.52
     Not
    -0.51
     resourceCulture
    -0.49
     not
    -0.49
     AspNetCore
    -0.48
     ikkje
    -0.47
    POSITIVE LOGITS
     permitted
    0.65
     successful
    0.62
     accessible
    0.61
    WriteTagHelper
    0.60
     capable
    0.59
     applicable
    0.59
     advisable
    0.59
     available
    0.59
     obtainable
    0.59
     feasible
    0.58
    Activations Density 4.300%

    No Known Activations