© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150045
    Prev
    Next
    INDEX
    Explanations

    displaying menu options

    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_23_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
     _$
    0.36
    하게
    0.36
    させて
    0.36
     triệu
    0.36
     अगु
    0.36
     Belediyesi
    0.35
     pulgadas
    0.35
     tái
    0.35
     ẞ
    0.34
    டுத்து
    0.34
    POSITIVE LOGITS
    ales
    0.48
    imacy
    0.46
    ALES
    0.44
    Amazon
    0.43
    łąd
    0.42
    ಸ್ತ
    0.41
     berths
    0.40
    ali
    0.40
    名は
    0.39
    erenza
    0.39
    Activations Density 0.001%

    No Known Activations