INDEX

Explanations

words ending in -ary or otherwise relating to warnings and beginnings

oai_token-act-pair · gemini-2.0-flash

warnings or negative outcomes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<bos>

-1.06

 autorytatywna

-0.60

Và

-0.52

Datuak

-0.47

WriteLiteral

-0.47

География

-0.45

-0.43

ichtung

-0.42

로그램

-0.42

нент

-0.42

POSITIVE LOGITS

tagHelper

0.81

zielle

0.77

 مشين

0.75

RenderAtEndOf

0.74

oleic

0.69

 {}".

0.68

 Saltar

0.67

 unrecogn

0.67

TypedDataSet

0.66

epres

0.66

Activations Density 1.786%

words ending in -ary or otherwise relating to warnings and beginnings

warnings or negative outcomes

No Comments

No Known Activations