© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209311
    Prev
    Next
    INDEX
    Explanations

    island or pooling effects

    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_10_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
    d
    0.55
    st
    0.52
    line
    0.52
    loid
    0.51
    িনবার্গ
    0.50
     زيادة
    0.49
     oxid
    0.48
    stid
    0.47
    q
    0.47
    睺
    0.47
    POSITIVE LOGITS
     ISLAND
    0.77
     island
    0.71
    ]
    0.69
     pooling
    0.68
     pools
    0.68
    م
    0.68
    島の
    0.67
    Island
    0.66
     Pooling
    0.64
    ח
    0.64
    Activations Density 0.017%

    No Known Activations