© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112146
    Prev
    Next
    INDEX
    Explanations

    likely to [verb]

    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_2_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
     метода
    1.20
    ၀
    1.05
    0
    1.04
     commerciales
    1.03
     ovog
    1.02
    もら
    1.02
    c
    1.00
    ۰۰
    0.96
     resTmp
    0.96
     geoLocation
    0.96
    POSITIVE LOGITS
     are
    1.41
    ை
    1.40
    л
    1.34
    ü
    1.30
    ン
    1.23
     of
    1.22
     the
    1.20
    ก
    1.18
     up
    1.16
    AL
    1.16
    Activations Density 0.000%

    No Known Activations