© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49669
    Prev
    Next
    INDEX
    Explanations

    bracketed examples

    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_31_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
     unlocked
    0.38
     una
    0.38
    UNSIGNED
    0.37
    둡
    0.37
    ᾗ
    0.37
    дна
    0.37
     warmer
    0.37
    prits
    0.36
    дко
    0.36
    captcha
    0.36
    POSITIVE LOGITS
    !]
    0.46
     ]
    0.45
    enstein
    0.45
     ])
    0.43
     "]
    0.42
    ...]
    0.42
    +]
    0.39
     ]),
    0.37
    ]}{\
    0.37
    ]
    0.36
    Activations Density 0.002%

    No Known Activations