© 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. 6237
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate importance, scale, medical discussions, relevance, relation, or size

    oai_token-act-pair · gemini-2.0-flash

    code-related terms or functions

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

    random mixed texts

    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
     Diſ
    -0.80
     Efq
    -0.75
     Eſ
    -0.68
     ")");
    -0.66
    \{\\
    -0.65
     Monfieur
    -0.65
    kowym
    -0.64
    ]='\
    -0.64
     Económica
    -0.64
     Perſ
    -0.64
    POSITIVE LOGITS
    InitVars
    0.63
    fjspx
    0.53
    utilisons
    0.52
     Paglinawan
    0.51
    AnimationsModule
    0.50
    DeleteBehavior
    0.50
     nas
    0.48
     للاسماء
    0.48
     (!__
    0.48
    lofen
    0.47
    Activations Density 0.651%

    No Known Activations