© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240914
    Prev
    Next
    INDEX
    Explanations

    direct speech reporting 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_25_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
     boulevard
    0.24
     вули
    0.24
    क्
    0.23
    ტორი
    0.23
    任意の
    0.23
    ⿹
    0.23
     classifiers
    0.22
     stu
    0.22
     বয়স
    0.22
    ⬮
    0.22
    POSITIVE LOGITS
     La
    0.26
     segura
    0.25
     yazd
    0.25
     Aye
    0.24
     União
    0.24
     Lai
    0.24
     давления
    0.24
     autore
    0.24
     Nai
    0.24
    zął
    0.24
    Activations Density 0.000%

    No Known Activations