© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6217
    Prev
    Next
    INDEX
    Explanations

    parts of citations, including author names, publication names, volume numbers, and page numbers

    oai_token-act-pair · gemini-2.0-flash

    editing-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Editing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AutoScaleMode
    -0.66
    enterOuterAlt
    -0.65
     XMLHttpRequest
    -0.57
    resizingMask
    -0.56
    migrationBuilder
    -0.56
    ppins
    -0.53
     Fama
    -0.53
    extAlignment
    -0.52
     Majefty
    -0.51
     kasarigan
    -0.51
    POSITIVE LOGITS
     edited
    1.49
     editor
    1.48
     edit
    1.47
     editing
    1.41
     editors
    1.38
     Editor
    1.31
    Edited
    1.26
    edited
    1.25
    editor
    1.24
    Editor
    1.23
    Activations Density 2.152%

    No Known Activations