© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3180
    Prev
    Next
    INDEX
    Explanations

    words that express the idea that something is nearly impossible or of little value

    oai_token-act-pair · gemini-2.0-flash

    un words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WebElementEntity
    -0.65
     Cannot
    -0.60
    Impossible
    -0.59
    Cannot
    -0.58
    cannot
    -0.56
     cannot
    -0.54
    difficult
    -0.53
     invokingState
    -0.53
    impossible
    -0.53
    Difficult
    -0.52
    POSITIVE LOGITS
     un
    1.92
     uns
    1.34
     Un
    1.30
    Un
    1.26
     unt
    1.16
    un
    1.09
     Uns
    1.04
     una
    1.03
     UN
    1.03
     und
    1.01
    Activations Density 2.670%

    No Known Activations