© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14645
    Prev
    Next
    INDEX
    Explanations

    the word "much"

    oai_token-act-pair · gemini-2.0-flash

    the word 'much' and comparative adjectives

    np_token-act-pair-logits · gpt-4o-mini

    much

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    XmlAccessType
    -0.72
     الحره
    -0.64
     nakalista
    -0.64
     ComVisible
    -0.60
     Normdatei
    -0.60
    Бахар
    -0.59
     good
    -0.59
    good
    -0.58
    InjectMocks
    -0.58
    Good
    -0.57
    POSITIVE LOGITS
     better
    0.84
     clearer
    0.73
     simpler
    0.73
     stronger
    0.72
     smarter
    0.72
     easier
    0.72
     safer
    0.71
     smoother
    0.71
     happier
    0.70
     tougher
    0.69
    Activations Density 0.503%

    No Known Activations