© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238879
    Prev
    Next
    INDEX
    Explanations

    card, Card, v-card

    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
    elijkheid
    0.41
    שת
    0.40
     Video
    0.38
    ِب
    0.38
    ziem
    0.37
    ವೀ
    0.37
    Universidad
    0.37
    षेक
    0.36
    tras
    0.36
    วันนี้
    0.36
    POSITIVE LOGITS
     appunto
    0.40
    仓库
    0.36
     сравнению
    0.36
     Target
    0.35
    下が
    0.35
    ํ
    0.35
     χωρίς
    0.34
     στό
    0.34
     Jno
    0.34
     cars
    0.34
    Activations Density 0.000%

    No Known Activations