© 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-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58715
    Prev
    Next
    INDEX
    Explanations

    omniscient narrator

    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_2_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
     it
    1.25
    )
    1.20
    G
    1.17
    K
    1.10
     for
    1.07
    F
    1.05
    ),
    1.02
    R
    1.02
    typen
    0.95
    konom
    0.94
    POSITIVE LOGITS
    يد
    1.55
    ้
    1.51
    ă
    1.38
    ü
    1.36
    е
    1.26
    ą
    1.26
    ão
    1.16
    ı
    1.16
    ță
    1.11
    어
    1.10
    Activations Density 0.001%

    No Known Activations