© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154165
    Prev
    Next
    INDEX
    Explanations

    Squ

    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_60_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
    ل
    0.58
    л
    0.57
    el
    0.56
    ル
    0.47
    ek
    0.47
    ল
    0.44
    ल
    0.43
    is
    0.42
    al
    0.42
    eee
    0.42
    POSITIVE LOGITS
     squ
    0.57
     squats
    0.49
     Squ
    0.48
    Squ
    0.47
     squid
    0.45
     स्क
    0.44
     scram
    0.43
     squamous
    0.42
     molyb
    0.40
     sc
    0.39
    Activations Density 0.000%

    No Known Activations