© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35169
    Prev
    Next
    INDEX
    Explanations

    file writing and data saving

    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_7_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
     которым
    0.47
     ovvero
    0.36
    দের
    0.35
    મ
    0.33
    虽然
    0.31
    লে
    0.30
    ین
    0.30
     صحیح
    0.30
    রা
    0.30
    ات
    0.30
    POSITIVE LOGITS
     a
    0.45
     are
    0.45
     an
    0.44
     be
    0.44
     the
    0.43
     $
    0.33
     is
    0.32
     on
    0.32
     \
    0.32
     $>
    0.32
    Activations Density 0.041%

    No Known Activations