© 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. 34506
    Prev
    Next
    INDEX
    Explanations

    opening book pages

    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
    Cabin
    0.33
     jer
    0.31
    STE
    0.30
    "":
    0.30
    WhiteElo
    0.30
     হ
    0.29
    өл
    0.29
     "$
    0.29
    тков
    0.29
    നോ
    0.28
    POSITIVE LOGITS
     harmed
    0.36
     pages
    0.34
     page
    0.33
     Pg
    0.32
     getan
    0.32
     harm
    0.32
    removed
    0.32
     páginas
    0.30
     pagine
    0.30
    page
    0.29
    Activations Density 0.004%

    No Known Activations