© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206500
    Prev
    Next
    INDEX
    Explanations

    database context and framework setup

    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_20_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
    成绩
    0.43
    गंध
    0.40
    ంతరం
    0.38
    बाड़ी
    0.38
    ValueOf
    0.37
    膻
    0.36
    우리
    0.36
     मानें
    0.35
     peril
    0.35
    人性
    0.35
    POSITIVE LOGITS
    endering
    0.44
    ters
    0.40
    omethyl
    0.37
    ્સ
    0.36
    djangoproject
    0.36
    iggers
    0.36
     &
    0.35
    founders
    0.35
    streamlit
    0.35
    ッカ
    0.35
    Activations Density 0.000%

    No Known Activations