© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3642
    Prev
    Next
    INDEX
    Explanations

    End-of-sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     mince
    0.16
    ठे
    0.16
    Tuy
    0.15
    UNIQUE
    0.15
     hallar
    0.15
    dout
    0.15
    dihydroxy
    0.15
    €™
    0.14
     pertama
    0.14
     pretence
    0.14
    POSITIVE LOGITS
    ся
    0.16
    ا
    0.16
    %)
    0.15
    nde
    0.14
    ten
    0.14
     ===========
    0.14
    vasive
    0.14
    𝑡
    0.14
    azi
    0.14
    𝚌
    0.14
    Activations Density 0.586%

    No Known Activations