© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43464
    Prev
    Next
    INDEX
    Explanations

    predict outcomes or transfers

    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_13_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
     numérique
    0.55
     powerhouse
    0.51
     いい
    0.50
     série
    0.48
     فضای
    0.48
    す
    0.48
    周知
    0.48
     newcomer
    0.47
     壁
    0.47
     Daim
    0.47
    POSITIVE LOGITS
    amination
    0.55
    enar
    0.54
    .}
    0.53
    )،
    0.52
    )
    0.51
    .”)
    0.50
    !)
    0.49
    })
    0.48
    find
    0.47
    rid
    0.47
    Activations Density 0.000%

    No Known Activations