© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80006
    Prev
    Next
    INDEX
    Explanations

    Раз followed by ви or ли

    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_0_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
     I
    1.74
    τή
    1.40
    จะ
    1.30
    த்தில்
    1.19
     cuddling
    1.19
    ૦
    1.17
     tacky
    1.15
    し
    1.13
    <0x80>
    1.13
    1.13
    POSITIVE LOGITS
    v
    2.48
    m
    2.42
    l
    2.03
    b
    1.98
    u
    1.91
    ON
    1.88
    ↵
    1.79
    7
    1.79
    f
    1.77
    r
    1.77
    Activations Density 0.000%

    No Known Activations