© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5708
    Prev
    Next
    INDEX
    Explanations

    sentences that state the goal or purpose of a study or experiment

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    立
    -0.50
    ﾟ
    -0.48
     ...
    -0.47
     beyond
    -0.45
    排水
    -0.45
    CONCLUSIONES
    -0.45
    vis
    -0.44
    tumblr
    -0.44
     came
    -0.44
    autoreleasepool
    -0.43
    POSITIVE LOGITS
    //
    0.66
    Tikang
    0.64
    expandindo
    0.63
    apunov
    0.60
    MessageOf
    0.60
    ⓧ
    0.59
    /*
    0.56
     this
    0.54
    such
    0.53
     such
    0.53
    Activations Density 4.396%

    No Known Activations