© 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-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130625
    Prev
    Next
    INDEX
    Explanations

    hope, fragile, broken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    ບໍ
    0.37
     כמה
    0.37
    OTROS
    0.36
     करते
    0.36
     यूजर्स
    0.35
     الاجابه
    0.35
    ᱲ
    0.35
     ऐसा
    0.35
    לא
    0.35
     фаразлары
    0.35
    POSITIVE LOGITS
    थोरो
    0.41
    <0xBA>
    0.38
     doping
    0.37
     heartfelt
    0.37
    鲮
    0.37
    dirname
    0.37
     om
    0.36
    currentRow
    0.36
     pén
    0.36
     która
    0.36
    Activations Density 0.000%

    No Known Activations