© 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. 5101
    Prev
    Next
    INDEX
    Explanations

    container registry

    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
     ceded
    2.90
    时候
    2.46
    mals
    2.37
     mourning
    2.33
     colloid
    2.27
    ે
    2.26
     lod
    2.22
    其他
    2.21
     thorns
    2.21
     عادي
    2.15
    POSITIVE LOGITS
    anı
    2.63
    ına
    2.63
    ১১
    2.57
    పాటు
    2.54
    anın
    2.53
     పాటు
    2.42
    bread
    2.37
    вчи
    2.30
    ছে
    2.30
    в
    2.28
    Activations Density 0.000%

    No Known Activations