© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    first-person narrative

    oai_token-act-pair · gemini-2.0-flash

    I

    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
     vie
    -0.36
     managing
    -0.35
     manage
    -0.34
     tie
    -0.33
     de
    -0.33
     his
    -0.33
     standing
    -0.33
     r
    -0.32
    ative
    -0.32
    ’
    -0.32
    POSITIVE LOGITS
     resourceCulture
    0.89
    NameInMap
    0.82
    styleType
    0.78
     فريبيس
    0.75
    AutoScale
    0.75
    EDEFAULT
    0.74
     Pyrene
    0.73
    twimg
    0.73
    FunctionFlags
    0.71
    UnusedPrivate
    0.71
    Activations Density 0.941%

    No Known Activations