© 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. 12893
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to religion and personal relationships

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    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
    COUVER
    -0.53
    DOCTYPE
    -0.49
    WEEN
    -0.46
     Lat
    -0.45
    vikling
    -0.45
     CURIAM
    -0.44
    出版年
    -0.44
    いって
    -0.42
    __':
    -0.41
     kasarigan
    -0.40
    POSITIVE LOGITS
     AssemblyProduct
    0.86
     propOrder
    0.85
    LookAnd
    0.82
     disambiguazione
    0.76
     myſelf
    0.75
     purpoſe
    0.74
    $_['
    0.71
     perfons
    0.71
     Roskov
    0.70
    makeConstraints
    0.68
    Activations Density 1.077%

    No Known Activations