© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35986
    Prev
    Next
    INDEX
    Explanations

    guilttripping, guilty pleasure

    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_31_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
     witness
    0.39
     শিষ
    0.38
     orthodox
    0.38
     applaud
    0.36
     Greenfield
    0.36
     能
    0.35
     biol
    0.35
    लोत
    0.35
    witness
    0.35
     Blowing
    0.35
    POSITIVE LOGITS
     guilt
    0.46
     guilty
    0.42
     Guilty
    0.42
    罪
    0.40
    Sc
    0.34
     Sc
    0.33
     ent
    0.33
    লাম
    0.33
    预算
    0.32
    턱
    0.32
    Activations Density 0.012%

    No Known Activations