© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29181
    Prev
    Next
    INDEX
    Explanations

    questions starting with "can", "are", "will", "no"

    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_10_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
    k
    0.39
    in
    0.38
    dl
    0.36
    t
    0.33
    kec
    0.33
    di
    0.32
    dwell
    0.32
    isierung
    0.32
    ti
    0.32
    kow
    0.30
    POSITIVE LOGITS
    ’
    0.40
     outright
    0.33
     sofa
    0.32
    _{
    0.31
    超過
    0.31
    ので
    0.30
    un
    0.29
     direta
    0.29
     стать
    0.29
     abrupt
    0.29
    Activations Density 0.110%

    No Known Activations