© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30855
    Prev
    Next
    INDEX
    Explanations

    care and help

    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
     really
    0.48
    Really
    0.47
    really
    0.45
     opravdu
    0.41
     preset
    0.40
     realmente
    0.40
     összef
    0.40
    =".$
    0.38
     guarante
    0.37
    Preset
    0.37
    POSITIVE LOGITS
     Whether
    0.45
    whether
    0.43
     whether
    0.41
     WHETHER
    0.41
     Tư
    0.41
     stuk
    0.40
     pakk
    0.39
     Blocking
    0.38
    Whether
    0.38
    ளாக
    0.38
    Activations Density 0.003%

    No Known Activations