© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202152
    Prev
    Next
    INDEX
    Explanations

    endings in multiple languages

    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_6_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
    uv
    0.98
    ate
    0.94
    ่า
    0.94
    ical
    0.92
    ல்
    0.91
    c
    0.89
    arm
    0.87
    secondary
    0.86
    ang
    0.86
    u
    0.85
    POSITIVE LOGITS
    يد
    1.02
    使用
    0.97
    １
    0.96
    1
    0.93
    ために
    0.91
     ר
    0.90
     הק
    0.90
     actuelle
    0.88
    お
    0.88
     arabe
    0.86
    Activations Density 0.000%

    No Known Activations