© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5783
    Prev
    Next
    INDEX
    Explanations

    java code including import, io, public, apache, tika, and exception statements

    oai_token-act-pair · gemini-2.0-flash

    dot

    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
    []
    
    -0.74
    ^(@)
    -0.72
    []);
    -0.67
    %");
    -0.67
    NUMX
    -0.66
    _();
    -0.66
    ~:
    -0.65
    _
    
    -0.64
     */;
    -0.63
    });*/
    -0.63
    POSITIVE LOGITS
     NSCoder
    0.93
    TemporalType
    0.90
    XmlAccessType
    0.88
    ChildScrollView
    0.83
    SocketAddress
    0.81
    FilterChain
    0.79
    ValueGeneration
    0.77
    BindingResult
    0.77
    ServletException
    0.75
    URLException
    0.75
    Activations Density 6.752%

    No Known Activations