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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13440
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks, some short words like "to", and words like "please" and "better".

    oai_token-act-pair · gemini-2.0-flash

    don't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     صوتيه
    -0.98
     للاسماء
    -0.92
     propOrder
    -0.87
     betweenstory
    -0.80
     незавершена
    -0.80
    ConstraintMaker
    -0.73
     @"/
    -0.69
    parsedMessage
    -0.68
    ArgsConstructor
    -0.67
    igshid
    -0.66
    POSITIVE LOGITS
     don
    0.54
     dont
    0.54
    dont
    0.50
     always
    0.49
    Dont
    0.47
    <bos>
    0.47
     Dont
    0.45
    ;*/
    0.44
     Don
    0.44
     resist
    0.42
    Activations Density 0.941%

    No Known Activations