© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86686
    Prev
    Next
    INDEX
    Explanations

    volume, interconnected chambers and voids

    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_18_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
    ブロ
    0.46
     Genetic
    0.43
    쿠
    0.43
    ＋
    0.42
    +
    0.42
     Bol
    0.42
     Boltzmann
    0.42
     subiect
    0.41
    bol
    0.39
     XOR
    0.39
    POSITIVE LOGITS
    cccnc
    0.48
     grapes
    0.43
     emptied
    0.42
     `{
    0.41
     вме
    0.40
    FilePath
    0.40
    ósfera
    0.39
     acceptez
    0.39
    ाया
    0.39
    ोला
    0.38
    Activations Density 0.032%

    No Known Activations