© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5657
    Prev
    Next
    INDEX
    Explanations

    headphones and amplifiers

    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_40_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
     ear
    1.20
     Ear
    1.00
    耳
    0.88
    Ear
    0.87
     ears
    0.74
    ear
    0.73
     EAR
    0.73
     耳
    0.67
     earl
    0.63
    耳朵
    0.63
    POSITIVE LOGITS
    Noise
    0.49
     noise
    0.46
    ̼
    0.45
    ويم
    0.44
     traceback
    0.42
    noise
    0.42
    wired
    0.41
     Wired
    0.41
     Noise
    0.41
     wired
    0.40
    Activations Density 0.010%

    No Known Activations