© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59897
    Prev
    Next
    INDEX
    Explanations

    libsodium encryption

    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_11_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
     वैसा
    0.58
    нена
    0.53
     sentido
    0.51
    नंतर
    0.51
    盽
    0.50
    冎
    0.49
    睉
    0.49
    /-}$
    0.49
     interpretación
    0.49
    䀎
    0.49
    POSITIVE LOGITS
    ↵
    0.63
    amo
    0.53
    EN
    0.52
    ach
    0.51
    ARK
    0.51
    8
    0.50
    3
    0.49
    +
    0.49
    opard
    0.48
    air
    0.47
    Activations Density 0.000%

    No Known Activations