© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7058
    Prev
    Next
    INDEX
    Explanations

    harmful or unethical content

    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_39_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
     discomfort
    0.53
    尷
    0.49
     awkward
    0.49
     frustrations
    0.48
     frustration
    0.48
     অস্ব
    0.46
     annoyance
    0.43
     inconvenience
    0.43
    ሎ
    0.43
     inconven
    0.42
    POSITIVE LOGITS
     horrific
    0.40
     sadistic
    0.39
     vile
    0.38
    avil
    0.37
    刚
    0.36
     экстре
    0.36
     rage
    0.36
     extremist
    0.35
     horrifying
    0.35
    耐
    0.35
    Activations Density 0.598%

    No Known Activations