© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5100
    Prev
    Next
    INDEX
    Explanations

    European Union

    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_3_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
    ি
    2.60
    ى
    2.60
    er
    2.42
    al
    2.29
    ől
    2.26
    ేవ
    2.25
    iendo
    2.19
    б
    2.18
    ل
    2.13
    Չ
    2.10
    POSITIVE LOGITS
    ান
    2.29
    杉
    2.28
    𝑨
    2.13
     enclosing
    2.13
     perpetually
    2.12
    ስ
    2.12
    }",
    2.11
    𝕤
    2.09
     razón
    2.07
     ramping
    2.07
    Activations Density 0.023%

    No Known Activations