© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212131
    Prev
    Next
    INDEX
    Explanations

    karma, reward, sin, merit, absolution

    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_19_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
     छह
    0.51
     six
    0.50
     sechs
    0.46
     choline
    0.46
    六
    0.46
    "><
    0.45
     करणे
    0.44
     goutte
    0.44
    谗
    0.44
    дентифика
    0.43
    POSITIVE LOGITS
    不同的
    0.45
    UNA
    0.44
    VERY
    0.43
    istasis
    0.42
     heist
    0.42
     shy
    0.41
     supposedly
    0.41
     banyaknya
    0.40
     unknowingly
    0.40
     WARRANTIES
    0.40
    Activations Density 0.000%

    No Known Activations