© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208422
    Prev
    Next
    INDEX
    Explanations

    have

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tre
    0.41
    Already
    0.41
    已
    0.41
    চ্
    0.39
     bosh
    0.39
    tre
    0.39
     вже
    0.39
     already
    0.37
    difficult
    0.37
    以
    0.36
    POSITIVE LOGITS
     been
    0.47
     class
    0.46
     Commitment
    0.46
     Prior
    0.45
     Been
    0.45
     prior
    0.44
    Been
    0.43
     PRIOR
    0.41
     papers
    0.41
     classes
    0.40
    Activations Density 0.001%

    No Known Activations