© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35093
    Prev
    Next
    INDEX
    Explanations

    state machine

    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_3_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
    هم
    0.62
    ।
    0.60
    ۔
    0.57
    。
    0.56
     it
    0.55
    iversary
    0.53
     возможность
    0.52
    یره
    0.52
     курса
    0.52
     борь
    0.52
    POSITIVE LOGITS
    g
    0.74
    ع
    0.68
    ක්
    0.61
    щем
    0.60
    дин
    0.58
    rägt
    0.57
    та
    0.57
     آب
    0.56
    iskup
    0.56
    endedores
    0.55
    Activations Density 0.006%

    No Known Activations