© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9041
    Prev
    Next
    INDEX
    Explanations

    self-assembly or molecular rearrangement

    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_40_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
     उड़ा
    0.37
     верну
    0.36
    )/(
    0.35
    ethanol
    0.35
    。）
    0.35
     سلسلہ
    0.35
    ).(
    0.34
    .(\
    0.34
    ブン
    0.33
     Knox
    0.33
    POSITIVE LOGITS
     supr
    0.52
    Su
    0.46
     chemists
    0.45
     супра
    0.44
     Supra
    0.42
    㡚
    0.42
     chemistry
    0.42
    Recognition
    0.42
    su
    0.41
     Rebek
    0.41
    Activations Density 0.021%

    No Known Activations