© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123579
    Prev
    Next
    INDEX
    Explanations

    vLLM serving

    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_3_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
    '
    0.95
    ور
    0.77
    aS
    0.75
    ’
    0.64
    '><
    0.63
     Câmara
    0.63
    };//
    0.61
    Doch
    0.61
    aat
    0.61
    ot
    0.60
    POSITIVE LOGITS
     scrutin
    0.81
    mate
    0.78
    е
    0.77
     noting
    0.76
    ם
    0.74
     peligro
    0.73
     i
    0.71
     serve
    0.70
    recogn
    0.70
     malicious
    0.70
    Activations Density 0.001%

    No Known Activations