© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140551
    Prev
    Next
    INDEX
    Explanations

    snail shells describe shape

    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_12_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
     resTmp
    0.55
    𝗨
    0.55
     వర
    0.54
     IMF
    0.53
    U
    0.53
     Macri
    0.52
     umbilical
    0.52
    Uw
    0.52
    ൌ
    0.52
     u
    0.52
    POSITIVE LOGITS
    acements
    0.51
    ங்கா
    0.45
     distinguishes
    0.43
    没
    0.42
    ReadAll
    0.42
     mappe
    0.42
     avanzando
    0.42
     Fewer
    0.42
    ah
    0.41
    ’,
    0.41
    Activations Density 0.001%

    No Known Activations