© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76239
    Prev
    Next
    INDEX
    Explanations

    safe for use with

    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_31_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
     ತೊ
    0.39
     Star
    0.38
     enact
    0.37
     ٿ
    0.37
    隀
    0.36
     visibly
    0.36
     handcuffs
    0.36
     schre
    0.35
     barric
    0.34
    ໃຊ
    0.34
    POSITIVE LOGITS
     careless
    0.39
     reflector
    0.37
    Invitation
    0.37
     situado
    0.35
     lakeside
    0.35
     reflection
    0.35
    Kf
    0.34
     सेंटर
    0.34
    REFLECTION
    0.34
    崙
    0.34
    Activations Density 0.006%

    No Known Activations