INDEX

Explanations

mathematical expressions, especially those involving variables.

oai_token-act-pair · gemini-2.0-flash

Code edge cases

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

 argint

-0.50

 becauſe

-0.49

يكب

-0.46

 figliu

-0.46

 fekete

-0.44

 bőr

-0.44

 Shakspeare

-0.44

 trasparente

-0.43

 creș

-0.43

 hysteresis

-0.42

POSITIVE LOGITS

0.76

URLException

0.60

 AssemblyTitle

0.58

Õ

0.57

Ê

0.57

Û

0.56

<0xF4>

0.56

ﬂ

0.55

Ë

0.55

Ø

0.54

Activations Density 57.352%

mathematical expressions, especially those involving variables.

Code edge cases

No Comments

No Known Activations