© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138809
    Prev
    Next
    INDEX
    Explanations

    corruption and activists

    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_12_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
     Andere
    0.56
    昂
    0.52
     Shankar
    0.51
    嗨
    0.51
     fler
    0.50
    ادل
    0.50
     Suzanne
    0.50
    很多
    0.49
     Nightingale
    0.49
    稳定
    0.49
    POSITIVE LOGITS
     bă
    0.57
    UAL
    0.54
    FER
    0.52
    AME
    0.51
    FRS
    0.50
     =
    0.49
    AMES
    0.48
     supernatants
    0.48
    LEY
    0.48
    .",
    0.47
    Activations Density 0.000%

    No Known Activations