© 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. 130705
    Prev
    Next
    INDEX
    Explanations

    Polish words, suffixes, or names

    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
     hypothes
    1.20
     on
    1.15
    on
    1.10
    ز
    1.08
    ди
    1.00
     categor
    0.94
     reorgan
    0.94
     by
    0.92
     majú
    0.92
    ма
    0.90
    POSITIVE LOGITS
    1.07
    k
    0.93
    "，
    0.79
    lng
    0.78
    तून
    0.77
    ERS
    0.75
    all
    0.74
    elt
    0.74
    lest
    0.74
    varande
    0.73
    Activations Density 0.000%

    No Known Activations