© 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. 127299
    Prev
    Next
    INDEX
    Explanations

    berry patch, blast, haveibeenpwned

    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
    ud
    0.73
    f
    0.72
    .
    0.68
    ne
    0.67
    w
    0.66
    ach
    0.66
    t
    0.66
    v
    0.66
    l
    0.65
    IG
    0.62
    POSITIVE LOGITS
    herlands
    0.70
    лити
    0.63
    تهم
    0.63
    ष्मान
    0.62
    сів
    0.62
     Organizing
    0.60
    atious
    0.60
    தேசம்
    0.59
    ाई
    0.57
    ление
    0.57
    Activations Density 0.000%

    No Known Activations