INDEX

Explanations

dates, numbers and law enforcement terms within a legal or news context.

oai_token-act-pair · gemini-2.0-flash

technical terms or code snippets

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

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.54

 فريبيس

-0.50

+:+

-0.50

 fusca

-0.48

 intangible

-0.47

 Hidden

-0.43

 Redacción

-0.43

Autoritní

-0.42

 algod

-0.42

CASCADE

-0.41

POSITIVE LOGITS

TagMode

0.69

 للمعارف

0.68

djangoproject

0.64

 Meksiku

0.63

JKLM

0.59

RectangleBorder

0.58

')['

0.57

 مواليد

0.57

CPtr

0.57

èdia

0.56

Activations Density 1.496%

dates, numbers and law enforcement terms within a legal or news context.

technical terms or code snippets

No Comments

No Known Activations