© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14731
    Prev
    Next
    INDEX
    Explanations

    lines that are markdown comments or code

    oai_token-act-pair · gemini-2.0-flash

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pacing
    -0.45
     sp
    -0.42
     Roskov
    -0.42
    T
    -0.41
    况
    -0.41
    HttpFoundation
    -0.40
    shtml
    -0.40
    orté
    -0.40
     “
    -0.40
    jar
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.95
    enumi
    0.93
     שוליים
    0.81
    enumii
    0.80
     transfieras
    0.78
    ########.
    0.75
    AndEndTag
    0.74
     <<<<<<<<<<<<<<
    0.73
     ModelExpression
    0.73
    SBATCH
    0.72
    Activations Density 1.635%

    No Known Activations