© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40389
    Prev
    Next
    INDEX
    Explanations

    prodigy

    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_11_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
    이스
    0.27
    ان
    0.26
    زی
    0.26
    ل
    0.25
     اڈ
    0.25
    ق
    0.24
    ار
    0.24
    ある
    0.24
    アス
    0.24
    عمل
    0.24
    POSITIVE LOGITS
     n
    0.24
     mourn
    0.22
     hong
    0.22
    ii
    0.21
     Houston
    0.21
     rau
    0.21
    Id
    0.21
    4
    0.21
     London
    0.20
     P
    0.20
    Activations Density 0.003%

    No Known Activations