© 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. 5786
    Prev
    Next
    INDEX
    Explanations

    text discussing the extraction of nickel from ores and Angular directives

    oai_token-act-pair · gemini-2.0-flash

    Metal extraction from ore

    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
    StoryboardSegue
    -0.85
     defaultstate
    -0.78
    "]];
    -0.73
    oa̍t
    -0.71
    tanleria
    -0.69
     "));
    -0.68
     kasarigan
    -0.68
    argout
    -0.67
    })();
    
    -0.65
     Савезне
    -0.65
    POSITIVE LOGITS
    væ
    0.49
    énération
    0.48
    quid
    0.45
    criture
    0.44
    TagMode
    0.43
    aset
    0.43
     sediment
    0.42
    σιμο
    0.42
    verte
    0.42
    verz
    0.42
    Activations Density 7.596%

    No Known Activations