© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167065
    Prev
    Next
    INDEX
    Explanations

    polite Japanese verbs

    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_56_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
     !!!
    0.46
     !!!!!
    0.44
     !!!!
    0.44
     !!,
    0.42
    !!.
    0.42
    も
    0.39
    !!!"
    0.39
    මුත්
    0.38
     بھی
    0.37
     !”
    0.36
    POSITIVE LOGITS
    iches
    0.30
     thinner
    0.30
     AE
    0.29
     embed
    0.29
    Collide
    0.29
     thin
    0.29
    dihydroxy
    0.29
    哑
    0.29
    質量
    0.28
     একে
    0.28
    Activations Density 0.000%

    No Known Activations