© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194121
    Prev
    Next
    INDEX
    Explanations

    entering or exiting a door

    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_4_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
     be
    1.13
    (
    1.11
    ে
    0.98
    et
    0.94
    AT
    0.90
    os
    0.89
    AN
    0.89
    $$
    0.83
    IT
    0.82
    =
    0.82
    POSITIVE LOGITS
     ampio
    1.14
     existencia
    1.08
    ם
    1.06
     interno
    1.02
     oscuro
    0.98
     intento
    0.98
     apag
    0.98
     IFSC
    0.96
     absoluto
    0.96
     Ι
    0.96
    Activations Density 0.000%

    No Known Activations