© 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. 15992
    Prev
    Next
    INDEX
    Explanations

    reports on Mitchell's recent commitment to Wake Forest's basketball team

    oai_token-act-pair · gemini-2.0-flash

    has

    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
    enterOuterAlt
    -0.64
     tả
    -0.59
     poffible
    -0.58
     ThemeData
    -0.58
     Cæsar
    -0.56
     bailando
    -0.55
     Philist
    -0.55
     Yamato
    -0.54
     Operand
    -0.53
     tramway
    -0.52
    POSITIVE LOGITS
    afficheront
    0.70
     تضيفلها
    0.60
    ValueStyle
    0.58
    :]:
    0.55
    UrlResolution
    0.54
    EndProject
    0.51
    esModule
    0.49
    LookAnd
    0.49
     resourceCulture
    0.48
    leigh
    0.47
    Activations Density 0.844%

    No Known Activations