© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245289
    Prev
    Next
    INDEX
    Explanations

    Cards Against Humanity

    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_40_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
    owment
    0.44
    Dot
    0.42
     atthakath
    0.40
    Iam
    0.38
     iot
    0.38
    Antib
    0.38
    UtcNow
    0.37
    엘
    0.37
     एनीमिया
    0.36
    Lam
    0.36
    POSITIVE LOGITS
     against
    0.50
     Against
    0.48
    лін
    0.48
    Against
    0.45
     tegen
    0.45
     Card
    0.45
     gegen
    0.44
     AGAINST
    0.43
     कार्ड
    0.43
     против
    0.42
    Activations Density 0.000%

    No Known Activations