© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 58093
    Prev
    Next
    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ort
    0.44
    ikken
    0.44
    يمه
    0.41
    痛
    0.41
    irman
    0.40
    Objet
    0.40
     Insight
    0.40
    asa
    0.39
    Determine
    0.39
    يهه
    0.39
    POSITIVE LOGITS
    v
    0.37
     disparate
    0.37
     μέρος
    0.36
    ड़े
    0.36
     இப்போது
    0.35
     e
    0.35
     』
    0.35
     phage
    0.34
     Dwayne
    0.34
     olun
    0.34
    Activations Density 0.000%

    No Known Activations