© 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. 13307
    Prev
    Next
    INDEX
    Explanations

    the word "a" and related words like "an", as well as words related to legal proceedings, such as "decision", "principle", and "case".

    oai_token-act-pair · gemini-2.0-flash

    legal evidence

    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
    CppMethod
    -0.59
     ExecuteAsync
    -0.57
    ftagPool
    -0.52
    LookAnd
    -0.50
     ddelweddau
    -0.50
    ativement
    -0.49
    encodeWith
    -0.49
    Tikang
    -0.49
     referenties
    -0.49
    UVWXYZ
    -0.48
    POSITIVE LOGITS
    BarItem
    0.58
    icate
    0.52
    ="@+
    0.52
    alism
    0.52
     Gale
    0.51
    Примі
    0.51
     colouring
    0.51
    yth
    0.50
    ύτε
    0.50
     gathered
    0.50
    Activations Density 1.637%

    No Known Activations