© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157809
    Prev
    Next
    INDEX
    Explanations

    intent of

    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_2_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
    és
    0.97
    r
    0.92
    ups
    0.89
    ants
    0.87
    ↵
    0.86
    ر
    0.86
    agar
    0.84
    hat
    0.83
    EE
    0.82
    uts
    0.82
    POSITIVE LOGITS
    ند
    1.15
    。
    1.12
     powied
    0.97
    లు
    0.84
     encontr
    0.83
     οποίο
    0.82
     ampli
    0.82
    ।
    0.82
    მდეგ
    0.80
    را
    0.80
    Activations Density 0.001%

    No Known Activations