© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175762
    Prev
    Next
    INDEX
    Explanations

    Proportionality, speed, locker ransomware

    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_24_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
     C
    0.44
     Part
    0.41
     Took
    0.40
     செய்தனர்
    0.40
     B
    0.40
     Intra
    0.40
     Worked
    0.39
     IQ
    0.39
     Dur
    0.39
     ذکر
    0.39
    POSITIVE LOGITS
    товый
    0.44
    сі
    0.40
    वाची
    0.40
    configurable
    0.38
     skyrocketing
    0.38
    鴿
    0.38
    ти
    0.38
    河南省
    0.38
    ँ
    0.37
     तित
    0.37
    Activations Density 0.000%

    No Known Activations