© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10578
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, code, and punctuation related to logical programming

    oai_token-act-pair · gemini-2.0-flash

    special characters and formatting in code

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

    Code snippets

    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
    ,
    -0.56
    DebuggerNonUser
    -0.56
    ↵↵
    -0.52
     vôtre
    -0.51
    .
    -0.48
    addContainerGap
    -0.47
    ।
    -0.46
    ɵɵ
    -0.44
    عام
    -0.43
    힐
    -0.43
    POSITIVE LOGITS
    #+#
    0.85
    RenderAtEndOf
    0.78
    SceneManagement
    0.75
    zzleHttp
    0.75
    });*/
    0.74
    หวัด
    0.72
    BASEPATH
    0.72
     Roskov
    0.70
     Autorizaciones
    0.70
    AnchorStyles
    0.69
    Activations Density 4.621%

    No Known Activations