© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205421
    Prev
    Next
    INDEX
    Explanations

    medical indications

    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_56_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
     я
    0.59
     tr
    0.53
     tre
    0.48
     тре
    0.47
     Ya
    0.44
    tre
    0.44
     Я
    0.43
    Ya
    0.43
     ya
    0.42
     TRE
    0.42
    POSITIVE LOGITS
    Indic
    0.77
     indication
    0.73
    indications
    0.69
     indications
    0.67
     Indications
    0.67
     medical
    0.66
    indication
    0.65
     médica
    0.64
    चिकित
    0.64
     indicated
    0.63
    Activations Density 0.001%

    No Known Activations