INDEX

Explanations

descriptions of scenic views

oai_token-act-pair · gemini-2.0-flash

views

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 itſelf

-1.27

 myſelf

-1.21

 faſt

-1.18

 themſelves

-1.15

 houſe

-1.14

 ſtate

-1.12

 Jefus

-1.12

 purpoſe

-1.08

 ſta

-1.05

 Majefty

-1.03

POSITIVE LOGITS

0.69

So

0.63

0.56

0.52

0.51

0.50

0.49

Activations Density 0.074%

descriptions of scenic views

views

No Comments

No Known Activations