© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12272
    Prev
    Next
    INDEX
    Explanations

    mentions of the direction "left" and directional comparisons.

    oai_token-act-pair · gemini-2.0-flash

    left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     незавершена
    -0.65
    featureID
    -0.61
     <>",
    -0.58
     createSprite
    -0.56
     rarity
    -0.56
     Depor
    -0.56
     CiNii
    -0.55
     PTE
    -0.52
     HasFactory
    -0.52
    ={`/
    -0.52
    POSITIVE LOGITS
    tvguidetime
    0.72
    Autoritní
    0.61
    CppMethod
    0.61
    CloseOperation
    0.56
     unknownFields
    0.56
     Tri
    0.56
    ؤول
    0.53
     Ab
    0.53
     CURIAM
    0.52
     متعلقه
    0.52
    Activations Density 2.276%

    No Known Activations