© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236160
    Prev
    Next
    INDEX
    Explanations

    Instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Remember
    0.49
     기억
    0.45
     Remember
    0.44
     Remembering
    0.44
     remembering
    0.43
     remember
    0.41
    记忆
    0.41
    Ｂ
    0.40
    ersch
    0.39
    remember
    0.39
    POSITIVE LOGITS
     താഴ
    0.47
     Indicator
    0.42
    answers
    0.42
     answers
    0.40
    tableFuture
    0.40
    解答
    0.40
     follow
    0.39
     seguir
    0.39
    ന്യാ
    0.38
     please
    0.37
    Activations Density 0.003%

    No Known Activations