© 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. 5338
    Prev
    Next
    INDEX
    Explanations

    prepositions like von, in, mit, für

    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
    twist
    1.23
    ية
    1.22
    ской
    1.19
    ონ
    1.18
    ী
    1.15
    श
    1.14
     spéciaux
    1.12
    습니다
    1.11
    ك
    1.10
    age
    1.10
    POSITIVE LOGITS
     PostgreSQL
    1.19
    u
    1.15
    ENGTH
    1.14
     ομά
    1.13
     aberrations
    1.13
    ЗИ
    1.11
    ดย
    1.11
     PSF
    1.11
    
    1.11
    uire
    1.09
    Activations Density 0.006%

    No Known Activations