© 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. 11452
    Prev
    Next
    INDEX
    Explanations

    numbered steps in a set of instructions

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and code snippets

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

    step

    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
    HasAnnotation
    -0.63
     circonstances
    -0.62
    sterious
    -0.60
     estekak
    -0.60
     zijne
    -0.58
    mnop
    -0.58
    Vorlage
    -0.56
    extAlignment
    -0.56
     Monfieur
    -0.56
    FromArray
    -0.55
    POSITIVE LOGITS
     createSlice
    0.57
    //
    0.52
     rac
    0.48
    hyung
    0.47
    Autoritní
    0.47
    backends
    0.46
    المناصب
    0.46
    pesa
    0.46
     getopt
    0.45
     zurück
    0.45
    Activations Density 0.555%

    No Known Activations