© 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. 5125
    Prev
    Next
    INDEX
    Explanations

    amic és, ait z

    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
     diante
    0.62
    न
    0.59
     endereco
    0.58
    újo
    0.57
    ί
    0.56
    দ
    0.55
    ত্যাশিত
    0.54
    ни
    0.53
    ත්මක
    0.53
     ample
    0.52
    POSITIVE LOGITS
    CZ
    0.51
    newcommand
    0.49
     அளவிற்கு
    0.48
     அளவுக்கு
    0.48
    Y
    0.46
    G
    0.44
    GING
    0.43
    leting
    0.42
    rangle
    0.42
    னித
    0.41
    Activations Density 0.001%

    No Known Activations