© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12294
    Prev
    Next
    INDEX
    Explanations

    the word "story" or "tale" sometimes with other related words

    oai_token-act-pair · gemini-2.0-flash

    story

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     story
    -2.03
    Story
    -1.84
    story
    -1.80
     STORY
    -1.79
     Story
    -1.78
    STORY
    -1.56
     stories
    -1.48
    Stories
    -1.38
    故事
    -1.34
     Stories
    -1.34
    POSITIVE LOGITS
    Datuak
    0.56
     about
    0.52
    })));
    0.51
     encomp
    0.51
    /**
    0.50
     insegna
    0.50
     îns
    0.49
     unearthed
    0.48
    abestanden
    0.48
     AssemblyTitle
    0.47
    Activations Density 1.195%

    No Known Activations