© 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. 227676
    Prev
    Next
    INDEX
    Explanations

    downtime, downturned, downtempo

    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
    (),
    0.95
    ]:
    0.93
    は
    0.91
    ﺎ
    0.90
    은
    0.87
    \}$,
    0.86
    UR
    0.85
    ﻮ
    0.84
    ])
    0.83
    ],
    0.83
    POSITIVE LOGITS
    y
    1.33
    n
    0.90
    t
    0.89
    el
    0.87
    um
    0.86
    dicke
    0.83
     Noch
    0.82
    i
    0.82
    durch
    0.80
    ty
    0.80
    Activations Density 0.000%

    No Known Activations