© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15027
    Prev
    Next
    INDEX
    Explanations

    parenthetical asides and emotional commentary

    oai_token-act-pair · gemini-2.0-flash

    Within parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    "])
    -2.41
     ]
    -2.39
    "]),
    -2.38
    "],
    -2.38
    ."]
    -2.33
    "]);
    -2.31
    ]");
    -2.28
    "]];
    -2.27
    "]);
    -2.25
    "]));
    -2.25
    POSITIVE LOGITS
    ঙ্
    0.47
    POLYGON
    0.38
     â
    0.36
    mäs
    0.35
     lược
    0.35
    fahrzeug
    0.35
    Ậ
    0.34
     Nowak
    0.34
    USR
    0.33
    सन्दर्भ
    0.33
    Activations Density 2.945%

    No Known Activations