INDEX

Explanations

sentences describing actions performed by people, sometimes in sequence or with objects

oai_token-act-pair · gemini-2.0-flash

through

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utafitiHapana

-0.71

Tikang

-0.69

XmlAccessorType

-0.68

出版年

-0.66

ettbewer

-0.60

initState

-0.58

脚注の使い方

-0.58

mybatisplus

-0.56

 Мексичка

-0.55

 fédé

-0.55

POSITIVE LOGITS

 through

1.10

through

1.02

 Through

1.01

Through

1.01

 THROUGH

0.82

THROUGH

0.80

 thru

0.78

 Durch

0.70

 attraverso

0.68

thru

0.67

Activations Density 0.656%

sentences describing actions performed by people, sometimes in sequence or with objects

through

No Comments

No Known Activations