© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134640
    Prev
    Next
    INDEX
    Explanations

    terrified

    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_6_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
    t
    1.23
    esi
    0.88
    y
    0.84
    liness
    0.83
    一
    0.82
    tan
    0.82
    agna
    0.79
    ly
    0.78
    er
    0.74
    äm
    0.73
    POSITIVE LOGITS
    ል።
    1.15
    "।
    1.14
     Cualquier
    1.13
    ].
    1.08
    ም።
    1.05
    の高い
    1.04
     Aunque
    1.03
    ClassObject
    1.02
     },
    1.02
    CharPtr
    1.01
    Activations Density 0.000%

    No Known Activations