© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7644
    Prev
    Next
    INDEX
    Explanations

    hyphens and en dashes

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ThroughAttribute
    -0.55
    subpackage
    -0.55
    interopRequire
    -0.52
    toPromise
    -0.52
    rungsseite
    -0.52
    faßt
    -0.52
    WSGI
    -0.51
    "}";
    -0.51
    ernalia
    -0.51
    ]=='
    -0.50
    POSITIVE LOGITS
     برانيه
    0.69
    ValueStyle
    0.66
    řízení
    0.54
    Duel
    0.54
    Datuak
    0.54
     notizia
    0.53
     paille
    0.51
    ThemeOverlay
    0.51
    ppure
    0.50
     оригіналу
    0.50
    Activations Density 1.018%

    No Known Activations