© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89970
    Prev
    Next
    INDEX
    Explanations

    Ganges

    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
    t
    0.75
    nál
    0.72
    𝕡
    0.71
    რო
    0.70
     플레이
    0.69
     tràn
    0.66
    ción
    0.66
    ците
    0.65
    цију
    0.64
     extérieur
    0.62
    POSITIVE LOGITS
    0.74
    .
    0.65
    ening
    0.57
     rechts
    0.57
    ิน
    0.54
    EM
    0.54
    يل
    0.53
    ริง
    0.53
    šu
    0.53
    、
    0.52
    Activations Density 0.000%

    No Known Activations