© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261331
    Prev
    Next
    INDEX
    Explanations

    knownknowledge

    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_5_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
     метода
    1.20
    ﻜ
    1.18
     lógica
    1.17
     ذریع
    1.14
     நகா
    1.14
    ли
    1.12
     готови
    1.10
    。
    1.10
     причине
    1.09
     accepté
    1.07
    POSITIVE LOGITS
     of
    2.11
    ה
    1.59
     in
    1.55
     )
    1.53
     (
    1.44
    จะ
    1.43
     }
    1.41
     and
    1.38
    1
    1.35
    ing
    1.31
    Activations Density 0.001%

    No Known Activations