© 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
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12499
    Prev
    Next
    INDEX
    Explanations

    the word "guide."

    oai_token-act-pair · gemini-2.0-flash

    guide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     guidance
    -1.37
     guide
    -1.21
     guides
    -1.19
     guiding
    -1.18
    guidance
    -1.09
     Guidance
    -1.09
    guide
    -1.05
    Guidance
    -1.02
     guidelines
    -1.02
     GUID
    -1.02
    POSITIVE LOGITS
    }\]
    0.81
    ScopeManager
    0.80
     >=",
    0.71
    }();
    0.71
     nakalista
    0.69
    Zitat
    0.68
    ViewFeatures
    0.68
    aarrggbb
    0.66
    quilibrium
    0.65
    MENAFN
    0.65
    Activations Density 0.705%

    No Known Activations