© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93820
    Prev
    Next
    INDEX
    Explanations

    say "ety" endings

    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_60_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
    et
    0.55
    ET
    0.50
    assigned
    0.48
     Et
    0.47
    i
    0.44
    etam
    0.44
    illum
    0.43
    ce
    0.42
    Eth
    0.42
    icons
    0.42
    POSITIVE LOGITS
     tranquillity
    0.55
     sadness
    0.46
     humour
    0.45
     ty
    0.44
     femininity
    0.44
     honourable
    0.44
     tranquility
    0.41
    ৮
    0.40
     excite
    0.40
     spontaneity
    0.40
    Activations Density 0.000%

    No Known Activations