© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14459
    Prev
    Next
    INDEX
    Explanations

    measurements, numbers, and references to stages and phases

    oai_token-act-pair · gemini-2.0-flash

    phases and stages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     път
    -0.48
    vartis
    -0.45
     préc
    -0.44
    жели
    -0.44
    KommentareTeilen
    -0.44
    MessageTagHelper
    -0.44
     BoxDecoration
    -0.43
    ък
    -0.43
    brush
    -0.43
    toThrow
    -0.43
    POSITIVE LOGITS
    Autoritní
    0.75
    MigrationBuilder
    0.74
     millioner
    0.69
    millions
    0.69
    itect
    0.68
    {{$
    0.68
     million
    0.66
    oredCriteria
    0.65
     hinweg
    0.65
    ullable
    0.65
    Activations Density 1.802%

    No Known Activations