© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57358
    Prev
    Next
    INDEX
    Explanations

    body positive, hot line

    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_11_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
    LFT
    0.52
    ତ୍
    0.49
    ශ්‍ය
    0.49
     avenge
    0.47
    foregroundView
    0.46
    entrance
    0.46
    堬
    0.46
    ၆
    0.46
    ຂໍ້ມ
    0.45
    traffic
    0.45
    POSITIVE LOGITS
     Mildred
    0.47
     CRUD
    0.46
    emics
    0.45
     Maa
    0.44
    aya
    0.44
     Buddhism
    0.44
     Hermione
    0.44
    ria
    0.43
     chaque
    0.42
    iping
    0.42
    Activations Density 0.011%

    No Known Activations