© 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. 130630
    Prev
    Next
    INDEX
    Explanations

    **what you'll do**

    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
    𒋗
    0.38
     Gesture
    0.38
     Beginning
    0.38
    Dequeue
    0.37
     ξεκ
    0.37
     massless
    0.36
    เคราะห์
    0.36
     ঘটনা
    0.36
    জনাব
    0.36
     Selanjutnya
    0.36
    POSITIVE LOGITS
    ന്നി
    0.39
    をや
    0.38
     lõ
    0.37
    乎
    0.36
     wiping
    0.34
     ú
    0.33
     Ony
    0.33
     ফেলতে
    0.32
     فکر
    0.32
     zu
    0.32
    Activations Density 0.000%

    No Known Activations