© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199561
    Prev
    Next
    INDEX
    Explanations

    alma mater

    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
     detonation
    0.48
     unravel
    0.48
     denaturation
    0.44
    pple
    0.43
     ecosystems
    0.43
     advice
    0.42
     malice
    0.42
    ’
    0.42
     adversarial
    0.41
     trustworthiness
    0.41
    POSITIVE LOGITS
    H
    0.56
    A
    0.52
    Begin
    0.47
     получить
    0.46
    R
    0.44
    D
    0.44
     گا۔
    0.41
    Ă
    0.41
    Visit
    0.40
    P
    0.40
    Activations Density 0.000%

    No Known Activations