INDEX

Explanations

distinct section delimiters and separators found in code and scientific writing

oai_token-act-pair · gemini-2.0-flash

separators

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 myſelf

-1.91

 itſelf

-1.87

Efq

-1.76

 Theſe

-1.74

 ―――――

-1.57

 themſelves

-1.53

 disambiguazione

-1.52

NUMX

-1.52

IntoConstraints

-1.52

 becauſe

-1.52

POSITIVE LOGITS

1.21

1.10

1.09

1.01

0.95

0.92

<eos>

0.91

0.90

↵↵

0.88

↵

0.85

Activations Density 2.604%

distinct section delimiters and separators found in code and scientific writing

separators

No Comments

No Known Activations