INDEX

Explanations

code, math equations, and vector notation

oai_token-act-pair · gemini-2.0-flash

Vectors and computer code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Vector

-2.28

 vector

-2.25

Vector

-2.11

 vectors

-2.02

vector

-1.96

 Vectors

-1.92

 VECTOR

-1.91

VECTOR

-1.76

vectors

-1.75

Vectors

-1.70

POSITIVE LOGITS

PyExc

0.56

ันท

0.52

تفصیلات

0.51

Jîn

0.50

merate

0.48

argout

0.47

 AssemblyTitle

0.46

braith

0.45

//});

0.44

AsUp

0.44

Activations Density 4.328%

code, math equations, and vector notation

Vectors and computer code

No Comments

No Known Activations