© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12095
    Prev
    Next
    INDEX
    Explanations

    `INTEGER PRIMARY KEY AUTOINCREMENT`

    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_40_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
     gst
    0.46
     api
    0.40
    api
    0.40
    溃
    0.40
    rao
    0.39
     fant
    0.38
     ornaments
    0.38
    ỡ
    0.38
     pests
    0.38
    vascular
    0.38
    POSITIVE LOGITS
    INTEGER
    0.55
     CHRISTIAN
    0.46
     INTEGER
    0.45
     BRIEF
    0.42
    ON
    0.42
     REAL
    0.41
    BOOLE
    0.41
     HREF
    0.41
     LEFT
    0.40
    COMP
    0.40
    Activations Density 0.164%

    No Known Activations