© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133702
    Prev
    Next
    INDEX
    Explanations

    Amiga computer

    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_50_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
    hashCode
    0.43
    پور
    0.42
    Jam
    0.38
     sh
    0.38
    JAM
    0.37
    ൊപ്പം
    0.37
    jam
    0.37
    )+"]
    0.36
    ἂ
    0.36
    Jones
    0.36
    POSITIVE LOGITS
    IAC
    0.47
     BWR
    0.43
     IAC
    0.43
     Bever
    0.42
     ARR
    0.42
     Irrigation
    0.41
     med
    0.40
     AVC
    0.40
     IMC
    0.40
     Schwe
    0.39
    Activations Density 0.004%

    No Known Activations