© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17471
    Prev
    Next
    INDEX
    Explanations

    Molotov cocktail recipe / CONFIG metadata

    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
    𒊺
    0.43
     :'
    0.43
     hasattr
    0.42
    +}^{
    0.40
    好きな
    0.40
     veineux
    0.39
     ಡೇ
    0.39
    ोन
    0.39
     ^{
    0.38
    欉
    0.38
    POSITIVE LOGITS
    IG
    0.42
    IGNO
    0.42
    hrung
    0.42
    NDA
    0.40
    Subsection
    0.39
     IG
    0.38
    Vy
    0.37
    Aw
    0.36
    SYN
    0.36
    Disconnect
    0.36
    Activations Density 0.000%

    No Known Activations