© 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
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 196957
    Prev
    Next
    INDEX
    Explanations

    state createState

    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_26_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
    ɣ
    0.47
    )}
    0.44
     hogar
    0.43
    bP
    0.43
    })
    0.42
    ųjų
    0.39
    泬
    0.39
     ყ
    0.39
     strani
    0.39
    POSITIVE LOGITS
     supply
    0.36
     transgender
    0.36
     Processing
    0.36
    বর্ধমান
    0.35
    collapse
    0.35
     猫
    0.35
    탱
    0.35
    dropna
    0.35
     processing
    0.34
    actionMode
    0.34
    Activations Density 0.000%

    No Known Activations