© 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. 35235
    Prev
    Next
    INDEX
    Explanations

    foregroundColor or background color

    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
    z
    0.37
    u
    0.36
    7
    0.34
    é
    0.33
    w
    0.32
    9
    0.31
    The
    0.30
    im
    0.29
    6
    0.29
    та
    0.28
    POSITIVE LOGITS
     to
    0.41
     at
    0.40
     ت
    0.34
     of
    0.34
     为了
    0.29
     and
    0.29
    ット
    0.29
     tại
    0.28
     t
    0.28
     ihe
    0.28
    Activations Density 0.000%

    No Known Activations