© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61145
    Prev
    Next
    INDEX
    Explanations

    herd mentality

    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_11_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
    isering
    0.59
     Акысыз
    0.54
     اكثر
    0.53
    FORMAN
    0.53
     virtuel
    0.53
     welchem
    0.53
    ഴിഞ്ഞ
    0.52
    ()];
    0.52
     Dispon
    0.51
     fondament
    0.50
    POSITIVE LOGITS
    ده
    0.56
     me
    0.50
     strength
    0.48
     reassure
    0.47
     want
    0.46
     selves
    0.45
     sluggish
    0.44
     people
    0.44
     I
    0.44
    speople
    0.44
    Activations Density 0.000%

    No Known Activations