© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204944
    Prev
    Next
    INDEX
    Explanations

    department names

    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_6_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
    as
    1.32
    ין
    1.30
    る
    1.22
    ה
    1.16
    ת
    1.16
    ের
    1.13
    의
    1.10
    at
    1.09
    و
    1.08
    ุ
    1.07
    POSITIVE LOGITS
    v
    1.70
    h
    1.15
    t
    1.13
    ta
    1.11
    ко
    1.06
    r
    1.02
    leri
    1.01
     agréable
    1.01
    ’
    0.97
    ke
    0.97
    Activations Density 0.000%

    No Known Activations