© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167530
    Prev
    Next
    INDEX
    Explanations

    echo

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    $--
    0.47
     Ranges
    0.41
    -->'
    0.40
     DNR
    0.39
    --,
    0.39
    }--\
    0.39
     دریافت‌شده
    0.39
     রিলি
    0.38
    -->
    0.38
     Differential
    0.38
    POSITIVE LOGITS
     "
    0.51
    ubert
    0.39
     "(
    0.38
     "../../
    0.38
    极为
    0.37
     );
    0.37
     ;(
    0.37
    url
    0.36
     "*
    0.36
     "/
    0.36
    Activations Density 0.001%

    No Known Activations