© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12688
    Prev
    Next
    INDEX
    Explanations

    date formats and related string manipulations

    oai_token-act-pair · gemini-2.0-flash

    parentheses and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     дописавши
    -0.92
     виправивши
    -0.90
    CloseOperation
    -0.90
    ftagPool
    -0.88
    Tikang
    -0.84
    WireFormat
    -0.81
     surla
    -0.79
    @[+][
    -0.79
    EDEFAULT
    -0.79
     ExecuteAsync
    -0.75
    POSITIVE LOGITS
     persoonlijke
    0.45
     elkaar
    0.43
     raggiung
    0.43
    あれば
    0.42
     nécessite
    0.41
     partag
    0.40
    むしろ
    0.40
     personlig
    0.40
     ordinaires
    0.39
     I
    0.39
    Activations Density 1.311%

    No Known Activations