© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202550
    Prev
    Next
    INDEX
    Explanations

    questions about

    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_12_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
    en
    0.69
    P
    0.67
    2
    0.59
    E
    0.58
    HL
    0.56
    un
    0.54
    other
    0.53
    any
    0.52
    ين
    0.52
    H
    0.52
    POSITIVE LOGITS
    这一切
    0.40
     ง
    0.39
     variété
    0.38
     variétés
    0.38
     Touchable
    0.37
    痈
    0.37
     auteurs
    0.36
     δι
    0.36
    ionage
    0.36
    ographie
    0.35
    Activations Density 0.004%

    No Known Activations