INDEX

Explanations

words related to teaching, user interfaces and sportswear.

oai_token-act-pair · gemini-2.0-flash

scales or quantities

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

脚注の使い方

-0.54

віть

-0.48

 Even

-0.48

ضا

-0.47

handleDelete

-0.46

 Kirke

-0.46

dean

-0.44

Even

-0.44

рс

-0.44

phyla

-0.44

POSITIVE LOGITS

__":

0.70

Personendaten

0.68

 propOrder

0.68

 Audiodateien

0.66

 للاسماء

0.65

__':

0.65

NameInMap

0.63

MigrationBuilder

0.63

tică

0.62

IUrlHelper

0.60

Activations Density 17.298%

words related to teaching, user interfaces and sportswear.

scales or quantities

No Comments

No Known Activations