© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126335
    Prev
    Next
    INDEX
    Explanations

    collaborative filtering or combination

    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_3_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
    0.69
    that
    0.64
    า
    0.61
    ണ
    0.61
    まず
    0.60
    a
    0.60
    aquest
    0.58
    oğlu
    0.58
    नून
    0.55
    ી
    0.55
    POSITIVE LOGITS
     Combination
    0.87
     COMB
    0.87
     komb
    0.84
     combinar
    0.84
     combination
    0.83
     on
    0.82
     combinación
    0.80
     combinação
    0.80
     combina
    0.79
     combinations
    0.79
    Activations Density 0.000%

    No Known Activations