© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127160
    Prev
    Next
    INDEX
    Explanations

    desolation

    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_3_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
     If
    0.88
     It
    0.81
    滘
    0.73
     Gunners
    0.71
     Premier
    0.65
    ض
    0.65
    нти
    0.64
    endan
    0.64
    们
    0.63
    ]
    0.63
    POSITIVE LOGITS
    l
    0.91
    canoe
    0.83
    sk
    0.83
    ca
    0.82
    sa
    0.82
    no
    0.81
    elle
    0.81
    ni
    0.79
    ah
    0.79
    la
    0.77
    Activations Density 0.000%

    No Known Activations