© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33847
    Prev
    Next
    INDEX
    Explanations

    plural marker 's'

    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
     to
    0.28
    0.27
     at
    0.24
     of
    0.21
     on
    0.19
     explosives
    0.18
     is
    0.18
    +:
    0.17
     embank
    0.17
     ICU
    0.17
    POSITIVE LOGITS
    و
    0.25
    ও
    0.22
    the
    0.22
    ف
    0.21
    in
    0.21
    The
    0.20
    s
    0.20
    N
    0.19
    d
    0.19
    การ
    0.18
    Activations Density 0.119%

    No Known Activations