© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248471
    Prev
    Next
    INDEX
    Explanations

    da/there

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    מה
    0.88
     מה
    0.83
     달
    0.79
    달
    0.75
    何
    0.71
    Dal
    0.70
     Dal
    0.66
     DAL
    0.63
     何
    0.60
    DAL
    0.59
    POSITIVE LOGITS
     da
    2.30
     Da
    1.80
     да
    1.79
    Da
    1.73
    da
    1.53
     دا
    1.50
     DA
    1.25
     다
    1.21
     då
    1.21
    دا
    1.07
    Activations Density 0.001%

    No Known Activations