© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4599
    Prev
    Next
    INDEX
    Explanations

    questions about ideas

    oai_token-act-pair · gemini-2.0-flash

    whether

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Bioaccumulative
    -0.40
     how
    -0.40
     veces
    -0.38
     Și
    -0.38
     lisäksi
    -0.38
     članak
    -0.38
     unable
    -0.38
    wnętr
    -0.37
    hark
    -0.36
    ğinde
    -0.36
    POSITIVE LOGITS
     anything
    0.79
     ANY
    0.76
     ANYTHING
    0.75
     any
    0.72
    anything
    0.71
    )‏
    0.71
    Anything
    0.71
    ValueStyle
    0.69
    __":
    0.69
     anybody
    0.68
    Activations Density 3.728%

    No Known Activations