© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206293
    Prev
    Next
    INDEX
    Explanations

    code itself returns True

    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_25_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
     adobe
    0.17
     depositors
    0.17
     deposit
    0.15
     depositing
    0.15
     annealing
    0.15
     proponents
    0.14
    Deposit
    0.14
    Ὁ
    0.14
     covenants
    0.14
     ಇನ್ನ
    0.14
    POSITIVE LOGITS
    cm
    0.15
    unz
    0.15
     Greens
    0.15
    初步
    0.14
     Hernandez
    0.14
    grep
    0.14
    的形式
    0.13
    itan
    0.13
    alámb
    0.13
    ..
    0.13
    Activations Density 0.004%

    No Known Activations