© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9244
    Prev
    Next
    INDEX
    Explanations

    code or configuration file parameters relating to cache, ports, buffers, and widths

    oai_token-act-pair · gemini-2.0-flash

    underscore/hyphen

    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
     purpoſe
    -0.71
     köln
    -0.65
     Himo
    -0.65
    Hochspringen
    -0.62
     ويكيميديا
    -0.62
     bogotá
    -0.61
    Filmografie
    -0.61
     raiſ
    -0.60
     reaſon
    -0.60
    amaño
    -0.60
    POSITIVE LOGITS
    dled
    0.44
    WriteTagHelper
    0.44
    jectures
    0.40
    setw
    0.39
    licted
    0.36
    secuted
    0.36
    proba
    0.36
    extendable
    0.35
    ciled
    0.35
    ndim
    0.35
    Activations Density 13.478%

    No Known Activations