© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24850
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     daughters
    0.38
    mets
    0.38
     }];
    0.37
    vanja
    0.37
     MS
    0.37
     Majka
    0.36
     pandemic
    0.36
    fiche
    0.36
     families
    0.35
     proliferation
    0.35
    POSITIVE LOGITS
    //
    0.50
    /**
    0.48
    োডে
    0.45
     //
    0.45
     /*
    0.42
    /*
    0.40
     //-->
    0.38
     /**
    0.38
    Clip
    0.38
    ///
    0.37
    Activations Density 0.003%

    No Known Activations