© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213401
    Prev
    Next
    INDEX
    Explanations

    Berkeley AI Research (BAIR)

    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_5_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
    ك
    2.08
     has
    1.84
    ה
    1.68
    ร
    1.66
    ين
    1.59
    з
    1.54
     on
    1.51
     with
    1.51
    к
    1.46
    נ
    1.44
    POSITIVE LOGITS
    um
    1.38
    -
    1.38
    1.31
    ong
    1.27
    ation
    1.25
    >
    1.17
    em
    1.16
    avaju
    1.16
    सी
    1.06
    ate
    1.05
    Activations Density 0.000%

    No Known Activations