© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76598
    Prev
    Next
    INDEX
    Explanations

    ’ followed by a letter or number

    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
     litt
    0.05
     recom
    0.04
    岳
    0.04
     gre
    0.04
     weight
    0.04
     patrolling
    0.04
    }-
    0.04
     Gell
    0.04
     acting
    0.04
     ECB
    0.04
    POSITIVE LOGITS
    埜
    0.06
     kültür
    0.05
    zwischen
    0.05
    हदी
    0.05
    の詳細
    0.05
    денциа
    0.05
    abbanti
    0.05
     regionales
    0.05
    হ্য
    0.04
    alloween
    0.04
    Activations Density 0.108%

    No Known Activations