© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59229
    Prev
    Next
    INDEX
    Explanations

    revamped [noun]

    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_2_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
    י
    1.61
    아
    1.37
    는
    1.35
    ী
    1.31
     to
    1.30
     that
    1.30
    ↵
    1.28
    ב
    1.25
    न
    1.23
    (
    1.22
    POSITIVE LOGITS
     are
    1.45
    வ்வேறு
    1.23
    druck
    1.15
    al
    1.11
    are
    1.07
    delt
    1.05
     as
    1.02
    dauer
    1.01
    theme
    1.00
    都
    0.98
    Activations Density 0.000%

    No Known Activations