© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45765
    Prev
    Next
    INDEX
    Explanations

    whale head

    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_3_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
    a
    0.82
    A
    0.75
    া
    0.75
    Treat
    0.73
    Have
    0.72
    Plasma
    0.71
    ]
    0.71
    )
    0.67
    Put
    0.66
    transpose
    0.65
    POSITIVE LOGITS
    ية
    0.79
    ور
    0.72
     endorsements
    0.71
    as
    0.70
    ő
    0.70
    ed
    0.70
     pequena
    0.70
    asının
    0.69
    ель
    0.68
    𝗂
    0.68
    Activations Density 0.005%

    No Known Activations