© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212253
    Prev
    Next
    INDEX
    Explanations

    talkative

    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
    ن
    1.67
    지
    1.48
    ন
    1.46
    न
    1.42
    น
    1.41
    in
    1.39
    수
    1.39
    在
    1.34
    리
    1.33
    ام
    1.30
    POSITIVE LOGITS
    3
    1.28
    ene
    1.16
    9
    1.09
    :
    1.08
    ert
    0.94
    uje
    0.94
    erti
    0.94
    <0x0D>
    0.92
     ersche
    0.91
    ype
    0.88
    Activations Density 0.002%

    No Known Activations