INDEX

Explanations

words related to gaming, points and rewards

oai_token-act-pair · gemini-2.0-flash

points

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

 hObject

-0.54

ÑOS

-0.46

orghini

-0.45

 EnglishChoose

-0.45

PMailer

-0.40

quelize

-0.40

vari

-0.40

filterBy

-0.40

 réserver

-0.39

ầm

-0.39

POSITIVE LOGITS

 points

2.66

points

2.31

 Points

2.28

Points

2.13

 POINTS

2.11

 point

2.08

point

1.88

 Point

1.81

POINTS

1.80

Point

1.79

Activations Density 3.124%

words related to gaming, points and rewards

points

No Comments

No Known Activations