© 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. 8823
    Prev
    Next
    INDEX
    Explanations

    conjunctions and interjections used to start new sentences (like so, and, but, that, yes)

    oai_token-act-pair · gemini-2.0-flash

    and/so

    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
    Mengapa
    -0.59
     how
    -0.56
     How
    -0.56
    why
    -0.54
     and
    -0.54
     pourquoi
    -0.53
    Pourquoi
    -0.52
    what
    -0.51
    WHY
    -0.50
    when
    -0.50
    POSITIVE LOGITS
    TagMode
    0.63
     numerus
    0.63
    aarrggbb
    0.62
    argout
    0.60
    MigrationBuilder
    0.60
    ]<<"
    0.59
    ContentAsync
    0.59
     OMITBAD
    0.57
     kasarigan
    0.57
    et
    0.56
    Activations Density 4.523%

    No Known Activations