INDEX

Explanations

the word "role" and other words that frequently appear near it

oai_token-act-pair · gemini-2.0-flash

role

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

tanleria

-0.93

 autorytatywna

-0.85

RenderAtEndOf

-0.81

ChildScrollView

-0.79

principalTable

-0.79

 فريبيس

-0.78

 GenerationType

-0.72

脚注の使い方

-0.71

 Anſ

-0.70

neté

-0.69

POSITIVE LOGITS

aspectj

0.48

in

0.48

 nello

0.45

 surla

0.44

onav

0.42

 deste

0.41

eterangan

0.40

Ос

0.40

OrBuilder

0.39

 trasferimento

0.39

Activations Density 3.092%

the word "role" and other words that frequently appear near it

role

No Comments

No Known Activations