© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165125
    Prev
    Next
    INDEX
    Explanations

    wickedness, cruelty, merciless

    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_13_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
    bee
    0.47
    साठी
    0.46
    incinnati
    0.46
    df
    0.45
     북
    0.44
    cong
    0.44
    emics
    0.43
    spur
    0.43
    鎸
    0.43
    Databaze
    0.43
    POSITIVE LOGITS
     vicious
    0.48
    न्होंने
    0.43
    隀
    0.42
     върху
    0.42
     merciless
    0.42
    鳃
    0.40
    ולנד
    0.40
     ruthless
    0.40
     Tiempo
    0.40
     Intellectual
    0.40
    Activations Density 0.000%

    No Known Activations