INDEX

Explanations

code snippets, version control terminology, and references to specific events or people associated with them.

oai_token-act-pair · gemini-2.0-flash

res

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

paksa

-0.68

Vidite

-0.60

 ویکی‌پدیای

-0.56

pośred

-0.55

actéristique

-0.54

 GenerationType

-0.53

éndole

-0.52

 magasiner

-0.51

(:,

-0.51

éndolo

-0.49

POSITIVE LOGITS

الإنجليزية

0.69

aarrggbb

0.57

0.51

IsContent

0.50

LookAnd

0.49

เพ

0.48

thora

0.47

oredCriteria

0.46

verti

0.46

queryInterface

0.46

Activations Density 9.792%

code snippets, version control terminology, and references to specific events or people associated with them.

res

No Comments

No Known Activations