© 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. 5563
    Prev
    Next
    INDEX
    Explanations

    descriptions of trails or paths

    oai_token-act-pair · gemini-2.0-flash

    technical terms and keywords

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

    paths

    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
     NSCoder
    -0.54
    BeginContext
    -0.52
    newtheorem
    -0.49
     reach
    -0.47
    InstanceState
    -0.46
    uxxxx
    -0.44
    expandindo
    -0.43
    providedIn
    -0.43
    一回
    -0.42
    Reach
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.74
    contentLoaded
    0.66
     nourrir
    0.63
    SourceChecksum
    0.60
    RTLD
    0.57
     vezet
    0.56
    __).
    0.55
     complètes
    0.54
    fony
    0.53
     Complexity
    0.53
    Activations Density 4.236%

    No Known Activations