© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214906
    Prev
    Next
    INDEX
    Explanations

    languages versions

    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_5_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
    מ
    1.39
    ות
    1.34
    ن
    1.32
    ৯
    1.23
    と
    1.21
    ای
    1.15
    中国
    1.14
    ட
    1.14
    ৮
    1.14
    خ
    1.13
    POSITIVE LOGITS
    ament
    1.15
    ни
    1.06
    ’
    1.06
    iff
    1.04
    ach
    1.02
    ating
    1.02
    ного
    1.02
     беше
    1.01
    charged
    0.99
    esthetics
    0.99
    Activations Density 0.000%

    No Known Activations