© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12379
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode commands

    oai_token-act-pair · gemini-2.0-flash

    LaTeX math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.70
     vPvB
    -0.63
    havior
    -0.55
    ranslated
    -0.54
     вікі
    -0.54
    Gruß
    -0.52
    ARROLL
    -0.51
     vôtre
    -0.51
     nôtre
    -0.50
    Jeografia
    -0.50
    POSITIVE LOGITS
    };*/
    0.67
    }>;
    0.66
    </i>
    0.64
    cu
    0.63
    __(/*!
    0.62
     []:
    0.60
    ConstraintMaker
    0.59
    IS
    0.59
    ();*/
    0.58
    })`
    0.57
    Activations Density 1.708%

    No Known Activations