© 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. 49968
    Prev
    Next
    INDEX
    Explanations

    typed array dimensions

    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
    Philos
    0.42
    獎
    0.39
     capitaine
    0.37
     зачем
    0.37
     philos
    0.37
     इनाम
    0.36
    blow
    0.36
    Reward
    0.36
    Flip
    0.36
    犢
    0.35
    POSITIVE LOGITS
     ابر
    0.37
    㴓
    0.37
    ادری
    0.36
    гласно
    0.36
    filterable
    0.36
    ຍ
    0.36
     establece
    0.36
     مقرر
    0.36
     wiped
    0.36
     eligibility
    0.35
    Activations Density 0.103%

    No Known Activations