© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210479
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     tub
    0.40
    Hare
    0.37
     tail
    0.36
    لاسه
    0.35
     rim
    0.35
     minuta
    0.34
    톰
    0.34
     harassing
    0.34
     Tub
    0.34
    ದಲ
    0.33
    POSITIVE LOGITS
    Го
    0.43
     বৎস
    0.40
    ._
    0.40
    数据的
    0.40
    関東
    0.40
    Ві
    0.38
    ANZ
    0.38
     അനുവദ
    0.38
     Sterne
    0.38
    🈺
    0.38
    Activations Density 0.000%

    No Known Activations