© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    works of fiction

    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
    스
    0.60
    фу
    0.58
    𝚝
    0.55
    ה
    0.52
    خانه
    0.51
    برای
    0.51
    𝚘
    0.51
    𝚊
    0.49
    ச
    0.49
     lucrative
    0.49
    POSITIVE LOGITS
     εί
    0.55
    inata
    0.50
    leman
    0.46
    bara
    0.46
     देखना
    0.45
    osoma
    0.43
    Tapi
    0.43
     π
    0.42
    ent
    0.42
     छोड़
    0.42
    Activations Density 0.098%

    No Known Activations