© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234417
    Prev
    Next
    INDEX
    Explanations

    renovated, modernized, or updated property features

    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_32_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
     крю
    0.44
     aparência
    0.38
    愺
    0.38
    த்தக
    0.38
    钩
    0.38
     Hooks
    0.37
     entera
    0.36
     prairie
    0.35
    个月
    0.35
     મહિના
    0.34
    POSITIVE LOGITS
     pens
    0.38
    ärts
    0.37
    ঈ
    0.36
     malt
    0.35
     Hilde
    0.35
     debts
    0.34
     equiv
    0.34
     meninggalkan
    0.34
    malt
    0.34
     supersonic
    0.33
    Activations Density 0.000%

    No Known Activations