INDEX

Explanations

the word "formed" and, to a lesser extent, the word "reaction".

oai_token-act-pair · gemini-2.0-flash

formed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Theſe

-1.35

 photolibrary

-1.25

RectangleBorder

-1.18

 greateſt

-1.18

 ―――――

-1.17

 surla

-1.13

 myſelf

-1.13

$_(

-1.11

 ſind

-1.10

 Anſ

-1.09

POSITIVE LOGITS

↵

0.76

0.75

0.66

0.63

 over

0.62

0.61

Activations Density 0.768%

the word "formed" and, to a lesser extent, the word "reaction".

formed

No Comments

No Known Activations