© 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. 6362
    Prev
    Next
    INDEX
    Explanations

    numbers and number-related symbols

    oai_token-act-pair · gemini-2.0-flash

    structured data elements

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

    numbers and codes

    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
     ujednoznacz
    -0.52
    pushd
    -0.52
    UnknownFieldSet
    -0.51
    internalType
    -0.51
     MainAxisSize
    -0.50
    skechers
    -0.47
    diff
    -0.46
    George
    -0.45
    george
    -0.45
     George
    -0.45
    POSITIVE LOGITS
    migrationBuilder
    0.66
     numerus
    0.62
     }}}
    0.54
    =?";
    0.54
    )":
    0.54
     */;
    0.54
    titleMargin
    0.54
    󠁣
    0.52
    ()")
    0.52
    Personendaten
    0.52
    Activations Density 3.644%

    No Known Activations