© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4540
    Prev
    Next
    INDEX
    Explanations

    the word 'abstract' and/or 'abstracts'

    oai_token-act-pair · gemini-2.0-flash

    abstract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Abstract
    -2.19
     Abstract
    -2.08
    abstract
    -2.06
     abstract
    -1.94
     ABSTRACT
    -1.48
    <bos>
    -1.45
    ABSTRACT
    -1.41
     abstracts
    -1.34
     abstrak
    -1.17
     abstra
    -1.12
    POSITIVE LOGITS
     ReactDOM
    0.69
    GEBURTS
    0.67
    gonic
    0.67
     Orion
    0.59
     igjen
    0.56
    AndEndTag
    0.55
    ViewInit
    0.54
    født
    0.54
    SpringRunner
    0.54
     Validators
    0.53
    Activations Density 0.292%

    No Known Activations