© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140744
    Prev
    Next
    INDEX
    Explanations

    bottleneck

    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_12_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
     to
    0.23
    де
    0.22
    to
    0.20
    کل
    0.20
    大
    0.20
    古
    0.20
    6
    0.20
    5
    0.20
     do
    0.19
    2
    0.19
    POSITIVE LOGITS
    rhe
    0.20
    riffe
    0.20
    :"))
    0.20
    abhuto
    0.20
     IAU
    0.20
     niezb
    0.19
     μαζί
    0.19
     MSA
    0.19
     Idha
    0.19
     لري
    0.19
    Activations Density 0.001%

    No Known Activations