© 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. 214528
    Prev
    Next
    INDEX
    Explanations

    radiant

    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
    و
    1.51
    ור
    1.29
    想到
    1.23
    ли
    1.19
    м
    1.19
     I
    1.17
    ো
    1.17
    AT
    1.16
    ру
    1.16
    م
    1.16
    POSITIVE LOGITS
    t
    1.97
    ad
    1.59
    q
    1.53
    b
    1.43
    st
    1.40
    c
    1.21
    ।
    1.20
    d
    1.17
    bc
    1.13
    w
    1.07
    Activations Density 0.000%

    No Known Activations