© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13495
    Prev
    Next
    INDEX
    Explanations

    RAID controllers, storage array, Erasure Coding

    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_40_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
     رکھتا
    0.41
    ]}"
    0.41
    )}"
    0.38
     mathcolor
    0.38
     Constructs
    0.38
     modulate
    0.37
    ventions
    0.37
     শৃঙ্খলা
    0.37
     constructs
    0.36
    ٽ
    0.36
    POSITIVE LOGITS
     Beck
    0.43
    પી
    0.40
     jõ
    0.40
     Tribute
    0.39
     Band
    0.39
     codes
    0.38
    Beck
    0.38
    weak
    0.37
     Pam
    0.37
    igy
    0.36
    Activations Density 0.034%

    No Known Activations