© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198576
    Prev
    Next
    INDEX
    Explanations

    saraswati

    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_15_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
     das
    0.51
    })$
    0.50
    ae
    0.47
    aus
    0.46
    idar
    0.46
    elen
    0.46
    atum
    0.45
    }
    0.45
    il
    0.44
     Mathematik
    0.44
    POSITIVE LOGITS
     جلوگیری
    0.54
     предотвра
    0.52
     muqueuse
    0.52
     PREVENTION
    0.52
     suffit
    0.52
    deleteOne
    0.49
     বিরত
    0.49
    ⟋
    0.49
     ሙ
    0.48
    ☚
    0.48
    Activations Density 0.000%

    No Known Activations