© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43774
    Prev
    Next
    INDEX
    Explanations

    superscript digits in chemical formulas

    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
    in
    0.71
    ες
    0.69
     powied
    0.67
    จะ
    0.66
    ۴
    0.66
    は
    0.65
    ם
    0.65
     aseptic
    0.64
    许
    0.63
    お
    0.63
    POSITIVE LOGITS
    ле
    1.03
    ne
    0.87
    z
    0.87
    ty
    0.86
    t
    0.84
    на
    0.82
    stvo
    0.80
    р
    0.79
    sts
    0.75
    wes
    0.74
    Activations Density 0.000%

    No Known Activations