INDEX

Explanations

sentences that describe the content of articles, media, policies, or reports

oai_token-act-pair · gemini-2.0-flash

documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

toThrow

-0.55

 Tienes

-0.43

-0.40

]<<"

-0.40

!</

-0.39

%!

-0.38

switch

-0.38

 Weyl

-0.38

 ſtate

-0.37

!")

-0.37

POSITIVE LOGITS

is

0.85

 utafitiHapana

0.82

SharedCtor

0.79

évaluateur

0.75

webElementXpaths

0.74

GEBURTSDATUM

0.71

 will

0.71

 includes

0.70

rubin

0.69

astéroïdes

0.68

Activations Density 1.416%

sentences that describe the content of articles, media, policies, or reports

documents

No Comments

No Known Activations