INDEX

Explanations

words related to the "Flo" substring, specifically "Floods" and "Floaters/Floating"

oai_token-act-pair · gemini-2.0-flash

Flo/flor

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

 lenker

-1.11

LookAnd

-0.87

 Roskov

-0.84

ReusableCell

-0.77

Rhestr

-0.76

AutoField

-0.75

SharedCtor

-0.75

+#+#

-0.73

unknownFields

-0.73

 henvisninger

-0.73

POSITIVE LOGITS

ori

0.62

ORI

0.57

ory

0.57

ora

0.56

lor

0.55

ories

0.54

oration

0.53

ors

0.53

orations

0.52

or

0.52

Activations Density 0.889%

words related to the "Flo" substring, specifically "Floods" and "Floaters/Floating"

Flo/flor

No Comments

No Known Activations