© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195201
    Prev
    Next
    INDEX
    Explanations

    consonance</consonance>

    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_4_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
    i
    1.09
    ’
    1.09
    assume
    1.08
    2
    1.07
    on
    1.02
    EC
    0.99
    PE
    0.97
    he
    0.96
    un
    0.95
    OU
    0.94
    POSITIVE LOGITS
     excitations
    0.86
    ttt
    0.86
    다
    0.86
     lineages
    0.85
    tiin
    0.83
     successors
    0.80
     adversaries
    0.80
     transgress
    0.80
     averse
    0.79
    tttt
    0.79
    Activations Density 0.002%

    No Known Activations