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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240996
    Prev
    Next
    INDEX
    Explanations

    lazy initialization and execution

    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
    }[!
    0.41
     Avec
    0.40
    ijker
    0.39
     tailles
    0.38
     ক্যাল
    0.37
    শিকান্ত
    0.37
    iens
    0.36
    ]^{
    0.36
     Atoms
    0.36
    ্য
    0.36
    POSITIVE LOGITS
     unscathed
    0.46
     ebenso
    0.40
     merciless
    0.40
     کامل
    0.39
     sifatida
    0.38
    planung
    0.38
     durumu
    0.38
     mutated
    0.37
     விசாரணை
    0.37
    🔷
    0.37
    Activations Density 0.001%

    No Known Activations