© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3515
    Prev
    Next
    INDEX
    Explanations

    project or entertainment

    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_5_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
    ло
    2.45
    ാ
    2.39
    an
    2.32
    inę
    2.27
    يارات
    2.21
    ações
    2.13
    ف
    2.10
    तौर
    2.07
     FileName
    2.05
    eers
    2.04
    POSITIVE LOGITS
     \%
    1.93
     kaya
    1.69
     huu
    1.69
    ㅋ
    1.67
    k
    1.64
     bass
    1.63
    к
    1.61
    튀
    1.60
    ठ
    1.60
    Зак
    1.58
    Activations Density 0.000%

    No Known Activations