© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68807
    Prev
    Next
    INDEX
    Explanations

    say "threatens"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     deprivation
    0.46
     robbed
    0.46
     rendered
    0.43
     deprived
    0.43
     amounted
    0.41
     deny
    0.40
    檸
    0.40
     deprive
    0.39
    樀
    0.38
    劫
    0.38
    POSITIVE LOGITS
     pit
    0.57
     explor
    0.51
    expl
    0.49
     pits
    0.48
    pit
    0.45
     EXPL
    0.45
    Pit
    0.45
     ble
    0.45
     ekspl
    0.44
     expl
    0.43
    Activations Density 0.008%

    No Known Activations