© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58560
    Prev
    Next
    INDEX
    Explanations

    lex fridman podcast

    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_2_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
    od
    1.44
    it
    1.33
    س
    1.30
    om
    1.30
    ok
    1.29
    ost
    1.28
    ow
    1.22
    es
    1.20
    id
    1.17
    os
    1.17
    POSITIVE LOGITS
    л
    1.57
    е
    1.34
    а
    1.08
    ллі
    1.06
    தான்
    1.05
    기
    1.05
    ل
    1.05
    ル
    1.05
    ću
    1.04
    ஆனால்
    1.03
    Activations Density 0.005%

    No Known Activations