© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 15117
    Prev
    Next
    INDEX
    Explanations

    words that describe the function and components of bicycle pedals or billiard cues

    oai_token-act-pair · gemini-2.0-flash

    movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     متعلقه
    -0.73
     становника
    -0.69
     برانيه
    -0.69
    __*/
    -0.67
    providedIn
    -0.65
     kasarigan
    -0.65
    Diweddarwch
    -0.64
     Meksiku
    -0.61
    adpleegd
    -0.61
     Normdatei
    -0.60
    POSITIVE LOGITS
     fyl
    0.46
    קישורים
    0.45
    rouvez
    0.43
    raszamy
    0.43
    PYX
    0.43
    férés
    0.42
     هيا
    0.42
    viewDid
    0.41
    ups
    0.40
     DSS
    0.40
    Activations Density 6.272%

    No Known Activations