© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162251
    Prev
    Next
    INDEX
    Explanations

    imprescindible immersion

    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_2_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
    0
    2.23
    3
    1.63
    ุ
    1.47
    و
    1.35
    ר
    1.24
    ের
    1.20
    7
    1.19
    ו
    1.17
    ০০
    1.16
    6
    1.16
    POSITIVE LOGITS
     as
    1.52
    S
    1.33
     are
    1.32
     be
    1.23
    너지
    1.12
    isub
    1.10
    것
    1.09
    L
    1.08
    p
    1.05
     obliter
    1.05
    Activations Density 0.001%

    No Known Activations