© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131042
    Prev
    Next
    INDEX
    Explanations

    End-to-End integration, encryption, project, virtual, flow

    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_6_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
    y
    1.67
    et
    1.51
    ↵
    1.31
    l
    1.29
    t
    1.26
    d
    1.23
    -
    1.20
    u
    1.16
    era
    1.14
    o
    1.14
    POSITIVE LOGITS
    ين
    1.02
     постро
    1.01
     hingegen
    0.92
    ༥
    0.91
     augmente
    0.90
     possibili
    0.90
     vardır
    0.89
     değer
    0.89
    其他
    0.89
     parametri
    0.88
    Activations Density 0.001%

    No Known Activations