© 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. 5128
    Prev
    Next
    INDEX
    Explanations

    code camp

    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
    ه
    2.12
    чис
    1.59
     hacerlo
    1.56
     ст
    1.54
    бто
    1.52
    ли
    1.51
     agua
    1.50
     cintura
    1.48
    arms
    1.48
    o
    1.47
    POSITIVE LOGITS
    ्य
    1.65
    نامه
    1.58
     समर्पित
    1.54
     summon
    1.52
    ϓ
    1.51
    lar
    1.46
     putri
    1.46
     AVAudio
    1.43
    ″
    1.41
    ل
    1.40
    Activations Density 0.002%

    No Known Activations