© 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. 85558
    Prev
    Next
    INDEX
    Explanations

    Apanasana, phantasia, Twin, aptX

    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
    ك
    0.86
    その
    0.84
    ка
    0.79
    ع
    0.74
    ف
    0.71
    ה
    0.70
     καθώς
    0.70
     defensor
    0.69
    过后
    0.68
    ق
    0.66
    POSITIVE LOGITS
    s
    0.86
    not
    0.84
    national
    0.75
    moment
    0.74
    malt
    0.74
    smith
    0.72
    notice
    0.72
    ،
    0.71
    natural
    0.71
    meeting
    0.70
    Activations Density 0.003%

    No Known Activations