© 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. 199905
    Prev
    Next
    INDEX
    Explanations

    filing status entities

    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
    I
    0.29
    Health
    0.25
    Pat
    0.25
    V
    0.24
    Everything
    0.23
    ARE
    0.23
    Rek
    0.23
    AM
    0.23
    Ill
    0.22
    Lightning
    0.22
    POSITIVE LOGITS
    '
    0.27
    odeled
    0.23
     CEO
    0.22
     scathing
    0.22
     relinqu
    0.21
    oqu
    0.21
    мули
    0.21
     relinquish
    0.21
    ́
    0.21
    锒
    0.21
    Activations Density 0.000%

    No Known Activations