© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92870
    Prev
    Next
    INDEX
    Explanations

    state createState() => _State

    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_11_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
    νο
    0.61
     accumulates
    0.58
     nucleotides
    0.56
    に
    0.55
    에
    0.53
     bells
    0.52
     boutons
    0.52
    </h3>
    0.52
     radial
    0.52
     accumulations
    0.52
    POSITIVE LOGITS
     că
    0.63
    porque
    0.62
    icht
    0.60
     माझ्या
    0.59
     jaren
    0.59
    aj
    0.57
     veel
    0.55
    because
    0.54
     omdat
    0.54
     karena
    0.54
    Activations Density 0.003%

    No Known Activations