INDEX

Explanations

code snippets, references to ranking, or entities, possibly related to data analysis or ethics.

oai_token-act-pair · gemini-2.0-flash

Harmful events

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 panels

-0.62

 paneles

-0.61

 boards

-0.60

مصادر

-0.60

Bronnen

-0.59

 Boards

-0.58

Controllers

-0.58

 matrices

-0.56

 tabs

-0.54

tabs

-0.54

POSITIVE LOGITS

 accidents

0.87

 crimes

0.85

 injuries

0.82

 marriages

0.79

 jobs

0.79

 diseases

0.77

 pregnancies

0.77

 appointments

0.76

 prosecutions

0.75

 loans

0.75

Activations Density 4.343%

code snippets, references to ranking, or entities, possibly related to data analysis or ethics.

Harmful events

No Comments

No Known Activations