© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201915
    Prev
    Next
    INDEX
    Explanations

    simultaneously contrasting states

    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_6_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
    м
    1.32
    로
    1.08
    し
    0.99
    ม
    0.96
    ل
    0.95
    ہ
    0.93
    αν
    0.93
    م
    0.93
     stone
    0.91
    ↵
    0.88
    POSITIVE LOGITS
    kind
    0.93
     أهم
    0.89
    csak
    0.89
    giv
    0.88
     affirme
    0.86
    OAc
    0.86
    fatter
    0.86
    kast
    0.85
    }\|^
    0.85
    forward
    0.85
    Activations Density 0.000%

    No Known Activations