© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168702
    Prev
    Next
    INDEX
    Explanations

    dent

    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
    сли
    0.39
     λογ
    0.39
    억
    0.38
    亿美元
    0.38
    ुलकर
    0.37
     unregistered
    0.36
    তেন
    0.36
    bolic
    0.35
    ኩል
    0.35
    )$\\
    0.35
    POSITIVE LOGITS
    al
    0.47
     aligns
    0.47
    ry
    0.45
    als
    0.45
    alnya
    0.44
    align
    0.44
     align
    0.44
    ал
    0.42
     aligned
    0.42
    ally
    0.42
    Activations Density 0.000%

    No Known Activations