© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201846
    Prev
    Next
    INDEX
    Explanations

    Medium

    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_37_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
     मीडियम
    0.41
    '),
    0.39
    Moderate
    0.38
     Threat
    0.37
     moderate
    0.37
     уско
    0.36
    Threat
    0.36
    }}}=
    0.35
    Criteria
    0.35
    kräft
    0.35
    POSITIVE LOGITS
     nameless
    0.39
     bookings
    0.39
    所に
    0.37
     कलेक्शन
    0.37
     子
    0.37
     fresh
    0.36
     Booking
    0.36
     Elliott
    0.36
     timeless
    0.35
    лянчук
    0.35
    Activations Density 0.011%

    No Known Activations