INDEX

Explanations

code snippets and related problem-solving discussions in languages other than English.

oai_token-act-pair · gemini-2.0-flash

negations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

RectangleBorder

-0.80

Eſ

-0.77

 Diſ

-0.77

 Reſ

-0.77

CodeAttribute

-0.72

 Theſe

-0.71

 سكانية

-0.70

 myſelf

-0.69

Efq

-0.69

ſelf

-0.68

POSITIVE LOGITS

 Insee

0.55

xase

0.46

ectoria

0.45

ther

0.43

 kuulu

0.40

з

0.39

BD

0.38

świad

0.38

uleiro

0.38

 igaz

0.38

Activations Density 0.615%

code snippets and related problem-solving discussions in languages other than English.

negations

No Comments

No Known Activations