© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6182
    Prev
    Next
    INDEX
    Explanations

    words related to requests and feelings of obligation or gratitude in the context of creative work and personal interactions.

    oai_token-act-pair · gemini-2.0-flash

    emoticons and punctuation marks

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

    emoticons

    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
    MENAFN
    -0.76
     Waray
    -0.75
    发表于
    -0.73
     محفوظة
    -0.71
    RefNanny
    -0.68
    _();
    -0.67
    、“
    -0.66
    NUMX
    -0.66
    Tikang
    -0.66
    、【
    -0.65
    POSITIVE LOGITS
     :
    1.55
     :)
    1.16
     :(
    1.15
    :)
    1.14
     (:
    1.13
     :-
    1.07
    (:
    1.06
     :]
    1.05
     ;)
    1.03
    :(
    1.02
    Activations Density 2.482%

    No Known Activations