© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    clauses including the words "that", "to", and pronouns such as "who".

    oai_token-act-pair · gemini-2.0-flash

    Keeping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    
    -0.75
    CodeAttribute
    -0.70
     للمعارف
    -0.69
    MethodManager
    -0.68
     SwitchCompat
    -0.65
    uxxxx
    -0.63
     BoxFit
    -0.62
     sẻ
    -0.60
    Citiți
    -0.59
     CreateTagHelper
    -0.58
    POSITIVE LOGITS
     kept
    1.40
     keep
    1.35
     keeping
    1.29
    keep
    1.23
     Keep
    1.23
    Keep
    1.21
     keeps
    1.19
    kept
    1.17
    Keeping
    1.15
    enter
    1.13
    Activations Density 3.435%

    No Known Activations