© 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. 38069
    Prev
    Next
    INDEX
    Explanations

    iSCSI followed by port or configuration

    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
    o
    0.91
     može
    0.71
    f
    0.70
    ed
    0.69
     불구하고
    0.68
     not
    0.67
    oa
    0.67
     febbraio
    0.67
    oč
    0.66
     postdoctoral
    0.66
    POSITIVE LOGITS
    ل
    0.84
    у
    0.79
    е
    0.75
    '
    0.74
    ll
    0.74
    τι
    0.70
    к
    0.69
    і
    0.69
    that
    0.66
    脂
    0.66
    Activations Density 0.000%

    No Known Activations