© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5299
    Prev
    Next
    INDEX
    Explanations

    sequences like "can reach"

    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_39_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
     अगला
    0.46
     Next
    0.45
    Next
    0.42
    の前
    0.40
     Berl
    0.40
    LastGen
    0.40
     মডেল
    0.40
    模
    0.40
    堇
    0.40
    敗
    0.40
    POSITIVE LOGITS
     reachable
    0.40
    wach
    0.39
    chains
    0.38
    igual
    0.38
    ('.')[
    0.38
     lizard
    0.37
    Mk
    0.37
     wak
    0.37
     custodia
    0.36
    saw
    0.36
    Activations Density 0.085%

    No Known Activations