© 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. 8492
    Prev
    Next
    INDEX
    Explanations

    phrases involving people giving information, opinions, or instructions, often with elements of doubt or uncertainty.

    oai_token-act-pair · gemini-2.0-flash

    uncommon or unusual word forms

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

    conversation/corrections

    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
     
    -1.34
     O
    -1.09
     (
    -1.08
     a
    -1.05
    ,
    -1.05
     B
    -1.04
    <eos>
    -1.04
     P
    -1.03
    ↵↵
    -1.02
     A
    -1.02
    POSITIVE LOGITS
     myſelf
    2.39
     itſelf
    2.28
     Efq
    2.17
     Monfieur
    2.13
    TagMode
    2.13
     ―――――
    2.11
     doubtnut
    2.06
    ſelf
    2.05
     faſt
    2.03
     Theſe
    2.03
    Activations Density 1.234%

    No Known Activations