© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153302
    Prev
    Next
    INDEX
    Explanations

    finding two numbers that sum

    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_23_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
     že
    0.42
    第二
    0.39
     daß
    0.38
     Versicher
    0.37
    ἕ
    0.37
     أن
    0.37
     że
    0.37
    病的
    0.37
    油
    0.36
     thứ
    0.36
    POSITIVE LOGITS
     inactivated
    0.42
     multicellular
    0.39
     distracting
    0.38
    పర్
    0.38
     pleated
    0.38
    Lambert
    0.38
    Ple
    0.38
     adsorbed
    0.37
    kapet
    0.36
     distracted
    0.36
    Activations Density 0.003%

    No Known Activations