© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245602
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
     awarded
    1.05
    胜
    1.05
    icians
    1.04
    铉
    1.04
    anth
    1.03
     ObjectMapper
    1.02
    čení
    1.02
    ونَ
    0.99
    лийн
    0.99
    agen
    0.97
    POSITIVE LOGITS
    ن
    1.20
    ির
    1.20
     tiempo
    1.19
    freq
    1.19
    ی
    1.19
    gespr
    1.18
    ल
    1.17
    ו
    1.16
    ിൽ
    1.15
    time
    1.15
    Activations Density 0.000%

    No Known Activations