© 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. 167723
    Prev
    Next
    INDEX
    Explanations

    heart

    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
    ஔ
    0.40
    簌
    0.36
     osl
    0.35
    ссажи
    0.35
     sustain
    0.34
     কীর
    0.34
    सं
    0.33
    𒈾
    0.33
     malad
    0.32
    חד
    0.32
    POSITIVE LOGITS
     hun
    1.78
     heart
    1.69
    heart
    1.38
     hunk
    1.35
     Hun
    1.32
    心
    1.30
    Heart
    1.28
    hun
    1.27
    Hun
    1.26
     Heart
    1.23
    Activations Density 0.001%

    No Known Activations