© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36123
    Prev
    Next
    INDEX
    Explanations

    things followed by punctuation or verbs

    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_11_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
     islet
    0.21
    in
    0.19
     isn
    0.19
    bien
    0.19
    infection
    0.19
     denkt
    0.19
    ’:
    0.18
    t
    0.18
    tors
    0.18
    town
    0.18
    POSITIVE LOGITS
    ，
    0.27
    ،
    0.23
    （
    0.22
    、
    0.21
    ।
    0.20
    ای
    0.20
    4
    0.18
     {
    0.18
    עה
    0.18
     musicians
    0.18
    Activations Density 0.021%

    No Known Activations