© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14021
    Prev
    Next
    INDEX
    Explanations

    negative numbers followed by or preceded by single digit numbers, or just division symbols followed by a number.

    oai_token-act-pair · gemini-2.0-flash

    Calculations and large numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    RenderAtEndOf
    -0.69
    出版年
    -0.66
     beginnetje
    -0.64
     متعلقه
    -0.61
     Roskov
    -0.59
    complexContent
    -0.55
     pleaſure
    -0.54
    ywna
    -0.54
    StoryboardSegue
    -0.54
     createSlice
    -0.53
    POSITIVE LOGITS
     fifteen
    0.70
     Sixteen
    0.65
     Fifteen
    0.65
    Fifteen
    0.64
    1
    0.57
     @"/
    0.57
    TacToe
    0.57
    mybatisplus
    0.55
     Seventeen
    0.55
     sixteen
    0.54
    Activations Density 1.320%

    No Known Activations