© 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. 14447
    Prev
    Next
    INDEX
    Explanations

    code with assignments and special characters

    oai_token-act-pair · gemini-2.0-flash

    equals sign

    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
    </blockquote>
    -0.45
    </strong>
    -0.42
    advanced
    -0.39
    </em>
    -0.38
    mach
    -0.37
     propriété
    -0.37
     entrevista
    -0.36
    ค
    -0.35
    ForType
    -0.35
    Pop
    -0.35
    POSITIVE LOGITS
    ConstraintMaker
    0.97
    findpost
    0.90
     jadx
    0.84
    MigrationBuilder
    0.84
    évaluateur
    0.81
    anyahu
    0.80
     transfieras
    0.80
     BoxDecoration
    0.79
    таратура
    0.78
    脚注の使い方
    0.77
    Activations Density 0.195%

    No Known Activations