© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12868
    Prev
    Next
    INDEX
    Explanations

    text related to software bugs and version numbers

    oai_token-act-pair · gemini-2.0-flash

    software release

    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
     betweenstory
    -0.67
    Personensuche
    -0.66
    Hochspringen
    -0.63
     ModelExpression
    -0.63
     صوتيه
    -0.60
    errHandler
    -0.58
     Normdatei
    -0.57
     AttributeSet
    -0.57
     Colette
    -0.56
    modelBuilder
    -0.56
    POSITIVE LOGITS
     releases
    0.66
     release
    0.58
     releasing
    0.57
     Releases
    0.55
    release
    0.53
    Release
    0.52
     kasarigan
    0.52
     Release
    0.51
    releases
    0.50
     rilas
    0.50
    Activations Density 4.080%

    No Known Activations