© 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. 142623
    Prev
    Next
    INDEX
    Explanations

    data identifiers

    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
    ك
    1.50
    ة
    1.39
    ری
    1.38
    um
    1.27
    ہ
    1.27
    ian
    1.21
    ει
    1.20
    1.20
    seits
    1.19
    ول
    1.16
    POSITIVE LOGITS
    I
    1.96
    s
    1.58
    ς
    1.54
    ים
    1.51
    ی
    1.48
    UZ
    1.44
    UCH
    1.43
    ב
    1.43
    ي
    1.41
    :
    1.41
    Activations Density 0.000%

    No Known Activations