© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2984
    Prev
    Next
    INDEX
    Explanations

    harmful or helpful 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
     superiore
    0.41
    reme
    0.40
     superiori
    0.38
    луч
    0.36
     Sinn
    0.35
     superior
    0.35
    dove
    0.35
    ":[
    0.35
     Superior
    0.34
    rope
    0.34
    POSITIVE LOGITS
     веду
    0.38
     revolving
    0.37
    стика
    0.36
    居家
    0.35
     reú
    0.35
     করিয়
    0.34
    amata
    0.34
    மிகு
    0.34
     yahoo
    0.34
     укра
    0.34
    Activations Density 0.041%

    No Known Activations