© 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. 8823
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to mathematical formulas and symbols.

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    MigrationBuilder
    -1.40
    rungsseite
    -1.14
     للاسماء
    -1.09
     ModelExpression
    -1.08
    yntaxException
    -1.06
    WriteBarrier
    -1.06
     tartalomajánló
    -1.05
    ConstraintMaker
    -1.05
    StoryboardSegue
    -1.04
     gynhyrchwyd
    -1.01
    POSITIVE LOGITS
     UN
    0.45
    ...
    0.41
     ne
    0.40
    UN
    0.38
     en
    0.36
     S
    0.36
    cal
    0.36
    v
    0.36
     os
    0.35
    顾
    0.35
    Activations Density 0.949%

    No Known Activations