© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75578
    Prev
    Next
    INDEX
    Explanations

    why other options are incorrect

    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_31_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
    ormal
    0.28
    途
    0.26
    লেখ
    0.25
    ojana
    0.25
     ord
    0.24
    ADO
    0.24
    Ano
    0.24
    oxo
    0.24
    adri
    0.24
    }^{[
    0.24
    POSITIVE LOGITS
    彧
    0.30
     பணியா
    0.29
     شدہ
    0.29
     Techniques
    0.28
     Methods
    0.27
    ágina
    0.27
    вера
    0.26
     একমাত্র
    0.26
     производится
    0.26
     OMB
    0.26
    Activations Density 0.043%

    No Known Activations