© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208492
    Prev
    Next
    INDEX
    Explanations

    relative spatial position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rifiuti
    0.48
     防止
    0.42
    verständlich
    0.42
     SSO
    0.41
     Kao
    0.40
    掊
    0.40
     JI
    0.40
    👗
    0.40
    🍱
    0.40
    ඝ
    0.40
    POSITIVE LOGITS
     Marcos
    0.45
     viajar
    0.45
     forced
    0.44
    youth
    0.44
    true
    0.44
    were
    0.43
    travel
    0.43
     যুব
    0.43
    lying
    0.42
    heading
    0.42
    Activations Density 0.004%

    No Known Activations