© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 344
    Prev
    Next
    INDEX
    Explanations

    words or short phrases expressing an opinion

    oai_token-act-pair · gemini-2.0-flash

    Online comments/conversations

    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
    TypedDataSet
    -1.05
     Roskov
    -0.91
    BeginContext
    -0.90
    RegressionTest
    -0.78
     '\\;'
    -0.76
     ModelExpression
    -0.75
     protoimpl
    -0.74
    setVerticalGroup
    -0.74
     يتيمه
    -0.72
    ніципа
    -0.72
    POSITIVE LOGITS
    PrivateRoute
    0.46
     Figure
    0.46
     энциклопедия
    0.46
    тивной
    0.45
     Hunt
    0.41
    tho
    0.41
     real
    0.41
    TargetException
    0.40
     pre
    0.40
     Rptr
    0.40
    Activations Density 2.693%

    No Known Activations