© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236522
    Prev
    Next
    INDEX
    Explanations

    fixed cost of

    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_25_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
     superstition
    0.44
     Capac
    0.41
     حدی
    0.38
     fascination
    0.38
     contradiction
    0.37
     normative
    0.37
     randomness
    0.36
    뮐
    0.36
     superstitious
    0.35
     Constance
    0.35
    POSITIVE LOGITS
    高效
    0.46
     deben
    0.38
     эффектив
    0.38
     uporab
    0.38
    </em>
    0.38
    дами
    0.38
    elab
    0.37
    çuk
    0.37
     department
    0.37
    वेद
    0.37
    Activations Density 0.001%

    No Known Activations