© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 306
    Prev
    Next
    INDEX
    Explanations

    text about some process, or about performing actions like writing or selling

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    felves
    -0.77
     ModelExpression
    -0.77
     TextInputType
    -0.73
     myſelf
    -0.72
     poffe
    -0.70
     Majefty
    -0.70
    ſelves
    -0.70
     leaſt
    -0.69
     perfons
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
    <bos>
    0.61
     disambiguazione
    0.59
    anera
    0.46
    etcode
    0.44
    })}$
    0.41
     dieux
    0.40
    UrlResolution
    0.39
    зулта
    0.39
    caire
    0.38
     gi
    0.38
    Activations Density 19.010%

    No Known Activations