© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201803
    Prev
    Next
    INDEX
    Explanations

    breaking encryption and drug discovery

    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_37_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
    circuit
    0.45
     circuit
    0.44
     Circuit
    0.41
    dete
    0.40
    Circuit
    0.39
    遺
    0.39
     CIRCUIT
    0.38
     сня
    0.38
    face
    0.37
    äte
    0.37
    POSITIVE LOGITS
     கற்க
    0.40
     installing
    0.39
     preaching
    0.39
     preach
    0.38
     morals
    0.38
    Список
    0.38
    槛
    0.37
     eserc
    0.36
     Hond
    0.36
     breaking
    0.36
    Activations Density 0.004%

    No Known Activations