© 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. 205852
    Prev
    Next
    INDEX
    Explanations

    contexts

    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
    f
    1.25
    ک
    1.24
    ه
    1.21
    其他
    1.20
    j
    1.17
    ین
    1.16
    ח
    1.15
    ہ
    1.14
    מ
    1.14
    т
    1.12
    POSITIVE LOGITS
    IT
    0.98
    AR
    0.80
    et
    0.77
    TER
    0.76
    ाई
    0.75
    2
    0.75
     fortsatt
    0.75
     Leiter
    0.73
    API
    0.72
    IFT
    0.72
    Activations Density 0.002%

    No Known Activations