© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3737
    Prev
    Next
    INDEX
    Explanations

    target/targeting, responsive

    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_40_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
    뮈
    0.37
    DetailUI
    0.37
    lua
    0.37
     Объ
    0.36
    ꯋ
    0.36
    люс
    0.36
    <0xF0>
    0.35
     स्ट्रा
    0.35
    쿤
    0.35
    symmetry
    0.34
    POSITIVE LOGITS
     targeting
    0.72
     Targeting
    0.71
     targeted
    0.67
     Targeted
    0.66
    Target
    0.64
     Target
    0.61
    targeting
    0.59
    targeted
    0.56
     target
    0.54
     responsive
    0.53
    Activations Density 0.019%

    No Known Activations