© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44601
    Prev
    Next
    INDEX
    Explanations

    root, 3rd, fifth, range, schemes, follow

    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_13_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
    ARE
    0.13
    Connecting
    0.12
    FreeBuf
    0.12
    Caribbean
    0.12
    Benzyl
    0.12
    蝴
    0.12
    Cream
    0.12
    Cx
    0.11
     porówn
    0.11
     paiement
    0.11
    POSITIVE LOGITS
     rogue
    0.13
     लेगा
    0.12
     Tale
    0.12
    </h1>
    0.12
    GISLATIVE
    0.12
     relevancia
    0.12
     "").
    0.11
     director
    0.11
     absur
    0.11
     rouge
    0.11
    Activations Density 0.009%

    No Known Activations