© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13467
    Prev
    Next
    INDEX
    Explanations

    devil, demon, maniac

    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_40_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
     stork
    0.37
     impatient
    0.37
     శు
    0.37
    वाली
    0.36
    職
    0.36
    ంచ
    0.36
    헷
    0.36
     nghĩa
    0.35
     faveur
    0.35
    달
    0.35
    POSITIVE LOGITS
    ('|
    0.43
    UtcNow
    0.39
    Ry
    0.39
     টিউ
    0.38
    ))).
    0.37
     NAN
    0.37
     تدخل
    0.36
    ्यों
    0.35
     intervention
    0.35
    Saw
    0.35
    Activations Density 0.036%

    No Known Activations