© 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. 5467
    Prev
    Next
    INDEX
    Explanations

    c++ code headers

    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
    ल
    2.98
    ல்
    2.54
    𝘞
    2.33
     headwinds
    2.29
    ح
    2.28
    Là
    2.24
    lem
    2.22
     zd
    2.22
    А
    2.22
     usize
    2.12
    POSITIVE LOGITS
    ‍♂️
    3.02
    माइंडर
    2.39
     Alexandria
    2.29
    ᶦ
    2.23
    ScriptAssemblies
    2.19
    тивний
    2.16
    менение
    2.14
     întâm
    2.13
    ])));
    2.08
     convicted
    2.06
    Activations Density 0.032%

    No Known Activations