© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129725
    Prev
    Next
    INDEX
    Explanations

    conjunctions and articles

    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_1_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
    ки
    1.30
    وں
    1.18
    おそらく
    1.09
    必要がある
    1.02
    お
    0.98
    نی
    0.96
    使う
    0.96
     apie
    0.95
     ঢাকায়
    0.94
    ابی
    0.93
    POSITIVE LOGITS
    us
    1.74
    T
    1.65
    M
    1.58
     that
    1.52
    id
    1.46
    D
    1.45
    that
    1.39
     (
    1.37
    ла
    1.30
    R
    1.30
    Activations Density 0.001%

    No Known Activations