INDEX

Explanations

angle brackets, dollar signs and code-related words

oai_token-act-pair · gemini-2.0-flash

title

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 initComponents

-0.60

 ""],

-0.59

DropTable

-0.57

 Majefty

-0.56

 podí

-0.56

 vocales

-0.55

waltung

-0.54

 espagne

-0.54

WebVitals

-0.53

 comigo

-0.52

POSITIVE LOGITS

انيف

0.57

 виправивши

0.56

 дописавши

0.50

DockStyle

0.50

ofar

0.49

TagMode

0.48

 mxArray

0.48

awaiter

0.46

 transfieras

0.46

FromArgb

0.45

Activations Density 20.316%

angle brackets, dollar signs and code-related words

title

No Comments

No Known Activations