© 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. 5241
    Prev
    Next
    INDEX
    Explanations

    its...its + noun/adjective

    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
    س
    2.28
    یکی
    1.74
    ために
    1.68
    sr
    1.59
    দ
    1.58
    ০০০
    1.54
    lah
    1.53
    dut
    1.53
     temer
    1.52
    accion
    1.51
    POSITIVE LOGITS
    er
    2.01
    い
    1.89
    ರ
    1.83
    ate
    1.80
     darkly
    1.70
    ق
    1.69
     laminar
    1.66
     lyophil
    1.63
    holding
    1.61
     physiologically
    1.60
    Activations Density 0.033%

    No Known Activations