© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208577
    Prev
    Next
    INDEX
    Explanations

    mid-point calculation

    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_25_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
     ή
    0.28
    ed
    0.27
     или
    0.26
     یا
    0.26
    或
    0.25
    ers
    0.25
     rad
    0.25
     song
    0.24
     or
    0.24
     oriented
    0.24
    POSITIVE LOGITS
     യു
    0.25
    빤
    0.25
    }+{\
    0.24
    работка
    0.24
    芋
    0.23
    งิน
    0.23
    ícios
    0.23
    መሪያ
    0.22
    वित
    0.22
     незавершена
    0.22
    Activations Density 0.007%

    No Known Activations