© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196710
    Prev
    Next
    INDEX
    Explanations

    synopses

    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_9_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
    1.59
    ن
    1.31
    n
    1.25
    v
    1.24
    of
    1.12
    m
    1.09
    j
    1.09
    and
    1.05
    r
    1.02
     of
    1.02
    POSITIVE LOGITS
    ího
    0.82
    ের
    0.80
    ség
    0.78
    íte
    0.78
    на
    0.77
     ئەو
    0.77
    transistors
    0.77
     cải
    0.76
     insectes
    0.75
    ો
    0.75
    Activations Density 0.001%

    No Known Activations