© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15514
    Prev
    Next
    INDEX
    Explanations

    cannot or impossible

    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_34_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
     confiscated
    0.38
     PB
    0.36
    числе
    0.34
     proffered
    0.34
     Whe
    0.34
    ટે
    0.34
     Samurai
    0.33
    鹤
    0.33
     Clos
    0.33
    较大
    0.33
    POSITIVE LOGITS
     couldnt
    0.64
     невозможно
    0.62
     couldn
    0.62
     Couldn
    0.60
     impossible
    0.57
    Couldn
    0.57
    impossible
    0.57
    cannot
    0.55
     нельзя
    0.52
    Impossible
    0.51
    Activations Density 0.089%

    No Known Activations