© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199187
    Prev
    Next
    INDEX
    Explanations

    sequences of letters

    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_27_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
    iques
    0.39
    Questo
    0.39
    ковых
    0.37
    sqrt
    0.37
    ringstream
    0.37
    फेक्शन
    0.36
     ontvangen
    0.36
    '],
    0.36
    ciendo
    0.36
    cyclohex
    0.36
    POSITIVE LOGITS
     hierarchy
    0.44
     hits
    0.41
     buys
    0.40
     mental
    0.40
     igra
    0.39
     beats
    0.39
     takeout
    0.39
    ంజ
    0.39
     dad
    0.38
     rentals
    0.38
    Activations Density 0.004%

    No Known Activations