© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246348
    Prev
    Next
    INDEX
    Explanations

    planning to go back

    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_40_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
     rah
    0.43
    इड
    0.39
     cull
    0.38
    frameNStart
    0.38
     Faisal
    0.37
     tigers
    0.36
    排
    0.36
     इस
    0.36
    प्ताह
    0.36
    沬
    0.36
    POSITIVE LOGITS
     novamente
    0.39
     igen
    0.39
    ново
    0.39
    㓞
    0.38
    ânica
    0.38
    ल्क
    0.38
    ல்களில்
    0.38
    介
    0.38
    혀
    0.38
     lấy
    0.38
    Activations Density 0.001%

    No Known Activations