© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65507
    Prev
    Next
    INDEX
    Explanations

    numerical weather forecast

    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_41_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
     Hol
    0.95
    Hol
    0.92
     hol
    0.77
     ambulatory
    0.71
     HOL
    0.63
     Ambul
    0.63
     Holt
    0.59
     홀
    0.58
     holster
    0.58
     होल
    0.56
    POSITIVE LOGITS
     ag
    0.40
     G
    0.40
     DBA
    0.39
     mez
    0.39
     B
    0.38
     avance
    0.38
    FV
    0.37
     comprom
    0.37
     points
    0.36
     compromise
    0.35
    Activations Density 0.003%

    No Known Activations