© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138026
    Prev
    Next
    INDEX
    Explanations

    memory safety and ownership

    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_12_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
    RAMM
    0.46
    t
    0.45
    tronic
    0.43
    ritional
    0.43
    ström
    0.43
     golongan
    0.43
    耠
    0.43
    </h2>
    0.43
    持续
    0.42
    शंस
    0.42
    POSITIVE LOGITS
     jeux
    0.59
    場合がございます
    0.54
     مؤرشف
    0.52
    affaire
    0.52
     mobilité
    0.51
     :
    0.50
     های
    0.50
     جه
    0.50
     بازی
    0.49
     Antrag
    0.49
    Activations Density 0.044%

    No Known Activations