© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6472
    Prev
    Next
    INDEX
    Explanations

    correspondence and documents

    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_39_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
    Resp
    0.38
    峙
    0.38
    Print
    0.37
    Princ
    0.37
     সন্ত্র
    0.37
     kidnapped
    0.35
    データを
    0.35
    祚
    0.35
     favored
    0.34
    Plastic
    0.33
    POSITIVE LOGITS
     letters
    0.45
     filing
    0.45
     Filing
    0.41
     correspondence
    0.41
     correspondance
    0.41
     diary
    0.39
     laundry
    0.39
     diaries
    0.38
     filed
    0.38
    correspond
    0.38
    Activations Density 0.031%

    No Known Activations