© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159169
    Prev
    Next
    INDEX
    Explanations

    eXplore, eXpand, eXploit

    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_2_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
    ר
    1.34
    l
    1.30
    er
    1.29
    en
    1.27
    st
    1.20
    ra
    1.16
    n
    1.16
    r
    1.16
    am
    1.14
    p
    1.13
    POSITIVE LOGITS
    ك
    1.41
    ],
    1.27
    ].
    1.27
    ).
    1.24
    נ
    1.23
    },
    1.18
    ко
    1.09
    ),
    1.08
     seguenti
    1.06
    υ
    1.04
    Activations Density 0.001%

    No Known Activations