© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 14410
    Prev
    Next
    INDEX
    Explanations

    the suffix "outs"

    oai_token-act-pair · gemini-2.0-flash

    consequences and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     hjemmes
    -0.60
     vanske
    -0.59
     nærm
    -0.58
     föruts
    -0.57
     rød
    -0.57
     dår
    -0.56
     årene
    -0.56
     Up
    -0.56
     borrowed
    -0.55
    "
    -0.55
    POSITIVE LOGITS
    */),
    0.80
    Bioaccumulative
    0.71
    ;";
    0.71
    ulipas
    0.68
    }))
    
    0.67
    PhysRevD
    0.67
    ;';
    0.66
    __":
    
    0.66
    stdc
    0.65
    )?;
    0.65
    Activations Density 0.702%

    No Known Activations