© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6407
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with subjective emotional reactions or literary criticism.

    oai_token-act-pair · gemini-2.0-flash

    Personal anecdotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     judging
    -0.47
    itrile
    -0.46
    rents
    -0.45
    tometer
    -0.45
     Bridget
    -0.45
    eos
    -0.44
     delegado
    -0.44
     plex
    -0.43
     lenti
    -0.43
     Euripides
    -0.43
    POSITIVE LOGITS
    Бахар
    0.82
    NameInMap
    0.79
    providedIn
    0.79
     referenties
    0.76
    RegistryLite
    0.71
     '\\;'
    0.70
    WebControls
    0.69
    expandindo
    0.68
     gynhyrchwyd
    0.66
    IsPostBack
    0.66
    Activations Density 7.457%

    No Known Activations