© 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. 5490
    Prev
    Next
    INDEX
    Explanations

    always-on

    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
    er
    2.89
    i
    2.40
    Ꮆ
    2.35
    ি
    2.32
    رش
    2.21
    as
    2.17
    an
    2.15
    erne
    2.15
    ことが多い
    2.14
    ্ব
    2.13
    POSITIVE LOGITS
     voulu
    2.58
     autant
    2.53
    ри
    2.50
     пожалуйста
    2.38
    t
    2.32
     lika
    2.29
     irgendwie
    2.28
     alerta
    2.22
    nement
    2.19
    𝐚
    2.12
    Activations Density 0.079%

    No Known Activations