© 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. 9085
    Prev
    Next
    INDEX
    Explanations

    the prefix "ret", especially when followed by "ali", "est", or "ino".

    oai_token-act-pair · gemini-2.0-flash

    variations of the root "ret"

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

    ret

    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
    Portail
    -0.86
     defaultstate
    -0.75
     autorytatywna
    -0.67
    KommentareTeilen
    -0.64
    addCriterion
    -0.60
     صوتيه
    -0.60
    GEBURTSDATUM
    -0.60
     ghiaccio
    -0.59
    AutoresizingMask
    -0.59
     raccol
    -0.59
    POSITIVE LOGITS
     ali
    0.48
     ir
    0.47
     imp
    0.44
     catch
    0.43
     cr
    0.43
    catch
    0.42
    pr
    0.41
    rans
    0.41
     inter
    0.41
    Tyran
    0.40
    Activations Density 0.547%

    No Known Activations