© 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. 162417
    Prev
    Next
    INDEX
    Explanations

    person's name

    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
    ib
    1.05
    و
    1.04
    ories
    1.03
    க்
    1.02
    在
    1.01
    rikt
    1.00
    ström
    0.99
    ation
    0.97
    ش
    0.96
    的
    0.95
    POSITIVE LOGITS
    ه
    1.68
    a
    1.59
    ה
    1.18
     persone
    1.17
    ва
    1.16
    ס
    1.16
    дом
    1.15
     Londra
    1.15
    (),
    1.13
     کولو
    1.13
    Activations Density 0.000%

    No Known Activations