© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148968
    Prev
    Next
    INDEX
    Explanations

    named days and weeks

    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_23_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
    ँची
    0.40
     tambien
    0.39
    ℅
    0.38
     diariamente
    0.38
     تمہ
    0.37
     أيضاً
    0.37
     megsz
    0.37
    닭
    0.37
     chiếm
    0.36
     मुर्
    0.36
    POSITIVE LOGITS
    updating
    0.40
    ส
    0.40
     Chrysler
    0.40
     IBM
    0.38
     Erd
    0.38
    সু
    0.38
     Bologna
    0.38
     Market
    0.37
     industry
    0.37
     Turing
    0.37
    Activations Density 0.000%

    No Known Activations