INDEX

Explanations

language used in legal documents

oai_token-act-pair · gemini-2.0-flash

legal and code texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

poti

-0.47

mathop

-0.45

 Morg

-0.44

erta

-0.44

 Savannah

-0.43

ire

-0.43

 ceiling

-0.42

asche

-0.42

 rege

-0.42

koord

-0.42

POSITIVE LOGITS

GEBURTSDATUM

0.84

IBOutlet

0.77

 مشين

0.76

ValueGeneration

0.75

sidemargin

0.74

setVerticalGroup

0.74

UnusedPrivate

0.73

ArgsConstructor

0.72

 ويكيميديا

0.72

 ISNI

0.71

Activations Density 3.333%

language used in legal documents

legal and code texts

No Comments

No Known Activations