© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3505
    Prev
    Next
    INDEX
    Explanations

    negative statements and contradictions

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords and phrases

    np_token-act-pair-logits · gpt-4o-mini

    Negative statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Theſe
    -0.68
    })*/
    -0.60
    });*/
    -0.59
    "]));
    -0.56
     houſe
    -0.56
     occaf
    -0.52
    >-->
    -0.52
    ')";
    -0.51
    Anlage
    -0.51
    //});
    -0.50
    POSITIVE LOGITS
    $_['
    0.60
     isInitialized
    0.60
     originate
    0.57
     have
    0.55
    writeField
    0.54
     inspire
    0.54
     imply
    0.54
     come
    0.54
     justify
    0.53
    Flow
    0.52
    Activations Density 2.467%

    No Known Activations