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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5436
    Prev
    Next
    INDEX
    Explanations

    parts of an iOS objective-c code block

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     caufe
    -0.45
     Credo
    -0.45
     fhew
    -0.44
     Phenomena
    -0.43
     Cinemas
    -0.42
    Bước
    -0.42
     occafion
    -0.42
     anglès
    -0.40
     Dominicana
    -0.40
     Deo
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.79
     }}"></
    0.65
    })();
    0.62
     '\\;'
    0.60
     Po
    0.59
    ThroughAttribute
    0.58
     initComponents
    0.58
    XmlAccessType
    0.58
    })()
    0.57
    rolls
    0.56
    Activations Density 8.780%

    No Known Activations