© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31196
    Prev
    Next
    INDEX
    Explanations

    if [subject] [verb]

    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_31_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
     fossero
    0.43
     pudiera
    0.37
     wären
    0.36
     fosse
    0.35
    GREAT
    0.35
    Were
    0.34
     hatte
    0.34
    㑒
    0.33
    were
    0.33
     were
    0.33
    POSITIVE LOGITS
    do
    0.36
     Leer
    0.35
     lar
    0.34
    read
    0.33
     Applies
    0.32
    쌍
    0.32
     contextual
    0.32
     relatable
    0.32
    とされる
    0.32
     merits
    0.32
    Activations Density 0.009%

    No Known Activations