© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122248
    Prev
    Next
    INDEX
    Explanations

    best [noun/superlative]

    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_37_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
    癶
    0.39
     সোসাই
    0.38
    )--(
    0.37
    IOUS
    0.37
     Dwyer
    0.36
    </li>
    0.36
    unicode
    0.36
    开口
    0.35
    Milliseconds
    0.35
    *{
    0.34
    POSITIVE LOGITS
     dome
    0.43
     τρόπο
    0.43
    更高的
    0.42
     معاملات
    0.40
    信息的
    0.40
     ঝামে
    0.39
    ètres
    0.39
     सूत्रकृ
    0.38
     domes
    0.38
     antihist
    0.38
    Activations Density 0.004%

    No Known Activations