© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101460
    Prev
    Next
    INDEX
    Explanations

    discussion about wording

    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_16_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
     literate
    0.50
    踰
    0.50
     थे
    0.49
     bewusst
    0.49
     எதிர்க
    0.49
    К
    0.49
     thrived
    0.47
    Т
    0.47
     unethical
    0.47
     Kald
    0.47
    POSITIVE LOGITS
    EM
    0.45
    ੜ
    0.44
    abre
    0.43
    atsi
    0.43
    illes
    0.38
    の時間
    0.38
    的其他
    0.38
    undi
    0.38
    abhar
    0.38
    olysis
    0.37
    Activations Density 0.000%

    No Known Activations