© 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. 104103
    Prev
    Next
    INDEX
    Explanations

    night event

    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
    ang
    1.70
    ot
    1.41
    ah
    1.33
    um
    1.23
    st
    1.17
    os
    1.15
    ن
    1.12
    ai
    1.10
    ،
    1.10
    od
    1.09
    POSITIVE LOGITS
    ان
    1.26
     is
    1.16
    లు
    1.02
    தான்
    0.96
     t
    0.95
    र
    0.94
    ی
    0.91
    ^{*}}
    0.89
     jūs
    0.89
    ρο
    0.88
    Activations Density 0.000%

    No Known Activations