© 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. 5195
    Prev
    Next
    INDEX
    Explanations

    words with non-latin scripts

    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
    𝐦
    2.49
    it
    2.48
    ⿶
    2.45
    itio
    2.44
    nung
    2.36
    pessoas
    2.34
    ﻭ
    2.22
     значений
    2.18
    le
    2.18
    ㇂
    2.16
    POSITIVE LOGITS
    гій
    2.06
    ^{*}}\
    2.06
     sulfide
    2.05
    ди
    2.00
    Tabla
    1.98
     quasi
    1.98
    वाया
    1.97
     година
    1.97
    currentState
    1.95
    ked
    1.94
    Activations Density 0.000%

    No Known Activations