© 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. 240822
    Prev
    Next
    INDEX
    Explanations

    but it

    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
     someday
    0.42
     pasting
    0.38
    ộm
    0.37
     indisc
    0.37
    ঙ
    0.37
    பல
    0.37
    গঞ্জে
    0.36
    வதில்லை
    0.36
    ḷ
    0.36
     recommending
    0.35
    POSITIVE LOGITS
     Kar
    0.45
     Ре
    0.44
     С
    0.43
     К
    0.43
     Nh
    0.43
     H
    0.43
     Module
    0.42
     Rek
    0.42
     Ха
    0.41
     Tra
    0.41
    Activations Density 0.007%

    No Known Activations